Um die anderen Arten von Veröffentlichungen zu diesem Thema anzuzeigen, folgen Sie diesem Link: Natural conversation.
Zeitschriftenartikel zum Thema „Natural conversation“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Zeitschriftenartikel für die Forschung zum Thema "Natural conversation" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Zeitschriftenartikel für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
1
Dipta, Dinar. „Conversation Analysis as a Discourse Approach to Teaching Speaking Skill“. JETLe (Journal of English Language Teaching and Learning) 1, Nr. 1 (31.10.2019): 1. http://dx.doi.org/10.18860/jetle.v1i1.7718.
Der volle Inhalt der QuelleAnnotation:
<p>Conversation comes as two ways communication used in daily activities. The large numbers of conversations lead some researchers to analyze it. Conversation has been the primary interest to language researchers since natural, unplanned, everyday conversation is the most commonly occurring and universal language genre (Riggenbach, 1999). Conversation is a speech activity in which all members of a community routinely participate. Among other approaches to discourse analysis used in teaching speaking, conversation analysis (CA) is one of the convenient practical devices in teaching oral English in the classroom. This paper aims to explore the theoretical basis for conversational analysis and examine the techniques applying a discourse approach to teaching speaking in the classroom.</p>
2
Joty, S., G. Carenini und R. T. Ng. „Topic Segmentation and Labeling in Asynchronous Conversations“. Journal of Artificial Intelligence Research 47 (22.07.2013): 521–73. http://dx.doi.org/10.1613/jair.3940.
Der volle Inhalt der QuelleAnnotation:
Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications. We present two new corpora of email and blog conversations annotated with topics, and evaluate annotator reliability for the segmentation and labeling tasks in these asynchronous conversations. We propose a complete computational framework for topic segmentation and labeling in asynchronous conversations. Our approach extends state-of-the-art methods by considering a fine-grained structure of an asynchronous conversation, along with other conversational features by applying recent graph-based methods for NLP. For topic segmentation, we propose two novel unsupervised models that exploit the fine-grained conversational structure, and a novel graph-theoretic supervised model that combines lexical, conversational and topic features. For topic labeling, we propose two novel (unsupervised) random walk models that respectively capture conversation specific clues from two different sources: the leading sentences and the fine-grained conversational structure. Empirical evaluation shows that the segmentation and the labeling performed by our best models beat the state-of-the-art, and are highly correlated with human annotations.
3
Saifudin, Akhmad. „Implikatur Percakapan dalam Studi Linguistik Pragmatik (Conversational Implicature in Pragmatic Linguistic Studies)“. JALABAHASA 16, Nr. 1 (10.06.2020): 15. http://dx.doi.org/10.36567/jalabahasa.v16i1.423.
Der volle Inhalt der QuelleAnnotation:
Tulisan ini membahas implikatur percakapan, yakni sebuah studi dalam ilmu linguistik pragmatik yang mengkaji maksud penutur dalam percakapan. Tujuan penulisan ini adalah untuk mendeskripsikan apa itu implikatur percakapan, bagaimana mengidentifikasi dan memaknai implikatur, serta mengapa penutur menggunakan implikatur dalam tuturannya. Untuk mengkaji permasalahan digunakan teori Grice tentang prinsip kerja sama (PK), maksim percakapan (MP), dan implikatur percakapan. Data percakapan diperoleh dari observasi percakapan natural antara penulis dan mahasiswa, serta percakapan di antara mahasiswa yang terjadi di lingkungan kampus. Hasil analisis menunjukkan bahwa pada dasarnya dalam setiap percakapan digunakan implikatur. Implikatur digunakan bukan karena tidak ingin bekerja sama dalam percakapan, tetapi ada alasan yang lebih diprioritaskan dan alasan tersebut tidak dapat mematuhi semua maksim dalam MP. Implikatur percakapan digunakan untuk tujuan efisiensi verbal, pengalihan tanpa berbohong, kesopanan, dan tujuan estetika, serta ironi. This paper discusses the conversational implicature, which is a study in pragmatic linguistics that examines the intent of speakers in conversation. The purpose of this paper is to describe what the conversational implicature is, how to identify and interpret the implicature, and why do speakers want to engage in implicature. To study the problem Grice's theory of the cooperative principle, maxims of conversation, and the conversational implicature are used. Conversation data is obtained from observations of natural conversations between writers and students, as well as conversations between students that occur on campus. The results of the analysis show that basically in every conversation the implicature is used; The implicature is used not because they do not want to cooperate in conversation, but because there are prioritized reasons and those reasons cannot comply with all maxims in maxims of conversation. The conversationalimplicature is used for the purpose of verbal efficiency, misleading to lying, politeness, and aesthetic purposes, as well as irony.
4
Althoff, Tim, Kevin Clark und Jure Leskovec. „Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health“. Transactions of the Association for Computational Linguistics 4 (Dezember 2016): 463–76. http://dx.doi.org/10.1162/tacl_a_00111.
Der volle Inhalt der QuelleAnnotation:
Mental illness is one of the most pressing public health issues of our time. While counseling and psychotherapy can be effective treatments, our knowledge about how to conduct successful counseling conversations has been limited due to lack of large-scale data with labeled outcomes of the conversations. In this paper, we present a large-scale, quantitative study on the discourse of text-message-based counseling conversations. We develop a set of novel computational discourse analysis methods to measure how various linguistic aspects of conversations are correlated with conversation outcomes. Applying techniques such as sequence-based conversation models, language model comparisons, message clustering, and psycholinguistics-inspired word frequency analyses, we discover actionable conversation strategies that are associated with better conversation outcomes.
5
Nishfullayli, Sa'idatun, Lea Santiar und Harni Kartika Ningsih. „Discourse Structure Analysis of Making Request in Japanese Conversation“. JAPANEDU: Jurnal Pendidikan dan Pengajaran Bahasa Jepang 8, Nr. 2 (25.12.2023): 94–110. http://dx.doi.org/10.17509/japanedu.v8i2.61548.
Der volle Inhalt der QuelleAnnotation:
Making requests (irai) is a genre of spoken interaction that is taught from the basic level of learning Japanese as a foreign language. A request is one of the speech acts that may raise face-threatening potentials. Understanding the stages of request appropriate to Japanese culture is thus essential for Japanese learners to achieve successful conversation. Therefore, conversation pedagogy by using a discourse approach is essential. This study investigates a potential structure gap in Japanese making-requests conversations realized in actual settings and textbook conversational models. By employing genre theory and interpersonal discourse of “Negotiation” as a qualitative discourse analytic method from the Systemic Functional Linguistics (SFL) perspective, this paper describes the gaps and some factors that potentially influence the structure of Japanese making-request conversation. Data were obtained from conversational texts in the Japanese language corpus named Japanese Natural Conversation Corpus and Japanese textbooks for elementary and middle adult learners. Regarding the structure, the results show no difference between conversations in textbooks and authentic ones at the stage level, but both differ at the phase level. There is no introduction to the problem, additional explanation, and confirmation phases in textbook conversational models. In addition, the absence of the phases, the differences in pre-condition content between textbook and authentic conversations, also the length of the reasoning phase, are assumed to be influenced by relational status between participants (tenor) as well as the imposition degree of the requested object.
6
Hassan, Mahmudul, Shahriar Shakil, Nazmun Nessa Moon, Mohammad Monirul Islam, Refath Ara Hossain, Asma Mariam und Fernaz Narin Nur. „Sentiment analysis on Bangla conversation using machine learning approach“. International Journal of Electrical and Computer Engineering (IJECE) 12, Nr. 5 (01.10.2022): 5562. http://dx.doi.org/10.11591/ijece.v12i5.pp5562-5572.
Der volle Inhalt der QuelleAnnotation:
<span>Nowadays, online communication is more convenient and popular than face-to-face conversation. Therefore, people prefer online communication over face-to-face meetings. Enormous people use online chatting systems to speak with their loved ones at any given time throughout the world. People create massive quantities of conversation every second because of their online engagement. People's feelings during the conversation period can be gleaned as useful information from these conversations. Text analysis and conclusion of any material as summarization can be done using sentiment analysis by natural language processing. The use of communication for customer service portals in various e-commerce platforms and crime investigations based on digital evidence is increasing the need for sentiment analysis of a conversation. Other languages, such as English, have well-developed libraries and resources for natural language processing, yet there are few studies conducted on Bangla. It is more challenging to extract sentiments from Bangla conversational data due to the language's grammatical complexity. As a result, it opens vast study opportunities. So, support vector machine, multinomial naïve Bayes, k-nearest neighbors, logistic regression, decision tree, and random forest was used. From the dataset, extracted information was labeled as positive and negative.</span>
7
HOPKINS, ZOË, NICOLA YUILL und BILL KELLER. „Children with autism align syntax in natural conversation“. Applied Psycholinguistics 37, Nr. 2 (16.01.2015): 347–70. http://dx.doi.org/10.1017/s0142716414000599.
Der volle Inhalt der QuelleAnnotation:
ABSTRACTPrevious experimental work has shown that verbal children with an autism spectrum disorder (ASD) converge linguistically, or align, with an interlocutor, and to the same extent as typical children. However, it is not known whether ASD children align in natural conversation. The studies presented in this paper aimed to address this issue. We measured syntactic alignment in ASD children, first using an experimental task, and second in natural conversation. We found that ASD and typical children aligned to the same extent in both tasks, suggesting that experimental findings about alignment in ASD are ecologically valid. We argue, however, that the experimental measurement of alignment overstates the prevalence of syntactic alignment in children's conversations.
8
Wimbassa, Muhamad Dwirizqy, Taswiyah Marsyah Noor, Salma Yasara, Vannesha Vannesha, Tubagus Muhammad Arsyah und Abdiansah Abdiansah. „Emotional Text Detection dengan Long Short Term Memory (LSTM)“. Format : Jurnal Ilmiah Teknik Informatika 12, Nr. 2 (05.07.2023): 158. http://dx.doi.org/10.22441/format.2023.v12.i2.009.
Der volle Inhalt der QuelleAnnotation:
Emotional Text Detection is a technique in natural language processing that aims to identify the emotions contained in conversations or text messages. The LSTM (Long Short-Term Memory) method is one of the techniques used in natural language processing to model and predict sequential data. In this study, we propose the use of the LSTM method for emotion detection in conversation. The dataset used is a conversational dataset that contains positive, negative, and neutral emotions. We process datasets using data pre-processing techniques such as tokenization, data cleansing and one-hot encoding. Then, we train the LSTM model on the processed dataset and obtain evaluation results using accuracy metrics. The experimental results show that the LSTM model can be used to detect emotions in conversation with a good degree of accuracy. In addition, we also conducted an analysis on the prediction results of the model and showed that the LSTM model can correctly identify emotions. In conclusion, the LSTM method can be used to detect emotions in conversation with a good degree of accuracy. This method can be used to improve user experience in chat applications and increase the effectiveness of human and machine interactions.
9
Lertpoompunya, Angkana, Nathan C. Higgins, Erol J. Ozmeral und David A. Eddins. „Head movement during natural group conversation and inter-annotator agreement on manual annotation“. Journal of the Acoustical Society of America 154, Nr. 4_supplement (01.10.2023): A111—A112. http://dx.doi.org/10.1121/10.0022958.
Der volle Inhalt der QuelleAnnotation:
During speech communication and conversational turn-taking, listeners direct their head and eyes to receive meaningful auditory and visual cues. Features of these behaviors may convey listener intent. This study designed a test environment, data collection protocol and procedures, and investigated head movement behaviors during self-driven conversations among multiple partners. Nine participants were tested in cohorts of three. Participants wore a headset with sensors tracked by an infrared camera system. Participants watched an audio-video clip, followed by a 5-min undirected discussion. The entire session was video recorded for annotation purposes. Two annotators independently coded the video files using the EUDICO Linguistic Annotator software application. Annotations were then co-registered with the head tracking data in post processing. Inter-annotator agreement demonstrated the desired reliability, thereby validating the procedures designed. Movement trajectories showed that there were individual differences on the head yaw distribution. The combination of objective measures of head movement and manual annotation of conversation behaviors provides a rich data set for characterizing natural conversations in ecologically valid settings. The measurement procedures and coding system developed here is a first step towards characterizing head movements during conversations needed to predict listening intent and to create actions based on those predictions.
10
Ansari, Tarique. „Conversational AI Assistant“. International Journal for Research in Applied Science and Engineering Technology 10, Nr. 11 (30.11.2022): 1169–72. http://dx.doi.org/10.22214/ijraset.2022.47554.
Der volle Inhalt der QuelleAnnotation:
Abstract: A conversational assistant is an intelligent conversational computing system designed to mimic human speech to provide automated online guidance and support. The growing benefits of conversational support have led to widespread adoption across many industries to provide virtual support to their customers. Conversation assistance uses methods and algorithms from his two fields of artificial intelligence: natural language processing and machine learning. However, the application has many challenges and limitations. This research reviews recent advances in conversation support using artificial intelligence and natural language processing. We highlight the main challenges and limitations of the current work and provide recommendations for future research investigations.
11
Lindsay, Laura, Chiara Gambi und Hugh Rabagliati. „Preschoolers Optimize the Timing of Their Conversational Turns Through Flexible Coordination of Language Comprehension and Production“. Psychological Science 30, Nr. 4 (12.02.2019): 504–15. http://dx.doi.org/10.1177/0956797618822802.
Der volle Inhalt der QuelleAnnotation:
Conversation is the natural setting for language learning and use, and a key property of conversation is the smooth taking of turns. In adult conversations, delays between turns are minimal (typically 200 ms or less) because listeners display a striking ability to predict what their partner will say, and they formulate a response before their partner’s turn ends. Here, we tested how this ability to coordinate comprehension and production develops in preschool children. In an interactive paradigm, 106 children (ages 3–5 years) and 48 adults responded to questions that varied in predictability but were controlled for linguistic complexity. Using a novel distributional approach to data analysis, we found that when children can predict a question’s ending, they leave shorter gaps before responding, suggesting that they can optimize the timing of their conversational turns like adults do. In line with a recent ethological theory of turn taking, this early competency helps explain how conversational contexts support language development.
12
Kum, Junyeong, und Myungho Lee. „Can Gestural Filler Reduce User-Perceived Latency in Conversation with Digital Humans?“ Applied Sciences 12, Nr. 21 (29.10.2022): 10972. http://dx.doi.org/10.3390/app122110972.
Der volle Inhalt der QuelleAnnotation:
The demand for a conversational system with digital humans has increased with the development of artificial intelligence. Latency can occur in such conversational systems because of natural language processing and network issues, which can deteriorate the user’s performance and the availability of the systems. There have been attempts to mitigate user-perceived latency by using conversational fillers in human–agent interaction and human–robot interaction. However, non-verbal cues, such as gestures, have received less attention in such attempts, despite their essential roles in communication. Therefore, we designed gestural fillers for the digital humans. This study examined the effects of whether the conversation type and gesture filler matched or not. We also compared the effects of the gestural fillers with conversational fillers. The results showed that the gestural fillers mitigate user-perceived latency and affect the willingness, impression, competence, and discomfort in conversations with digital humans.
13
Ermakova, Olga P. „Indirect responses in natural conversation“. International Journal “Speech Genres” 31, Nr. 3 (25.08.2021): 181–89. http://dx.doi.org/10.18500/2311-0740-2021-3-31-181-189.
Der volle Inhalt der QuelleAnnotation:
By indirect answers we mean answers to general questions which do not correspond to “yes” and “no”, and answers to special questions which do not literally correlate with the question words who, what, where, etc. The article examines the types of indirect responses in different structural and semantic types of dialogue. The article analyzes the features of indirect answers determined by the predictive relationship of concepts: place-goal, place-time, etc. Particular attention is paid to answers containing assessment, not determineded by the content of questions, as well as question-answer turns with why and what for. The article focuses on the informative volume of indirect answers, their insufficiency and redundancy. Indirect questions are used rather frequently. It is not possible to classify all of them, but all of them are undoubtedly associated with certain types of dialogue, speech genres, speech situations and with the psychological type of communication partners. As noted earlier, the logical connection of the categories place-goal, placetime, goal-cause, etc. leads to reversibility and predictability of situations, and in certain speech genres to the interchangeability of designating categories in the form of indirect answers. A specific feature of the dialogue, observed in different speech genres, is the response containing the characteristic of the person mentioned in the question, instead of the information in which the speaker is interested. The analysis of these responses reveals the organic connection between the evaluation and the reason. The use of counter-questions, and first of all, why- and what for-remarks, is caused by the specific nature of this phenomenon, which, despite the thorough research of N. D. Arutyunova, allows to see some interesting features in it. The article uses recordings of oral speech and some works of fiction, reproducing spoken dialogue.
14
Belainine, Billal, Fatiha Sadat und Hakim Lounis. „Modelling a Conversational Agent with Complex Emotional Intelligence“. Proceedings of the AAAI Conference on Artificial Intelligence 34, Nr. 10 (03.04.2020): 13710–11. http://dx.doi.org/10.1609/aaai.v34i10.7127.
Der volle Inhalt der QuelleAnnotation:
Chatbots or conversational agents have enjoyed great popularity in recent years. They surprisingly perform sensitive tasks in modern societies. However, despite the fact that they offer help, support, and fellowship, there is a task that is not yet mastered: dealing with complex emotions and simulating human sensations. This research aims to design an architecture for an emotional conversation agent for long-text conversations (multi-turns). This agent is intended to work in areas where the analysis of users feelings plays a leading role. This work refers to natural language understanding and response generation.
15
Stovall, Preston. „On the Natural Ground of Discursive Cognition“. Philosophical Topics 50, Nr. 1 (2022): 109–34. http://dx.doi.org/10.5840/philtopics20225016.
Der volle Inhalt der QuelleAnnotation:
Despite increasing interest in shared intentionality in both philosophy and the sciences over the last three decades, there has been little comparison of philosophical with empirical accounts of the phenomenon. At the same time, both philosophical and scientific investigations into shared intentionality as a ground of our cognition have developed into widespread research programs during this period. This has laid the groundwork for a productive conversation, across the sciences and humanities, about the nature of human cognition qua discursive or rational. In this essay, I map some of the conceptual terrain such a conversation would cover, and I consider some of the extant efforts to build explanatory bridges across research and conversational contexts—using the resources of one domain of understanding to help structure our understanding of another—to the benefit of both philosophical and scientific approaches to the study of human cognition.
16
Sudartinah, Titik. „A Conversation Analysis of Two-year-old Children’s Speech in Child-Adult Interactions“. Jurnal Obsesi : Jurnal Pendidikan Anak Usia Dini 7, Nr. 3 (20.06.2023): 3345–56. http://dx.doi.org/10.31004/obsesi.v7i3.4586.
Der volle Inhalt der QuelleAnnotation:
Social interactions with adults around them are the main exposures to language that children receive, and these contribute significantly to their development. In response to this, this article examines the participation of two-year-old children in conversations with adults, aimed at describing the parties initiating conversation topics and identifying the structure of the conversations. The research used a qualitative method in the form of a case study, involving 5 children aged two years and their parents as participants. The data were collected through recorded natural conversations between children and parents. The results show that topics in child-adult interactions can be initiated by both parties. Furthermore, children have been able to build a complete conversational structure, consisting of opening, turn-taking, and closing. Several components of turn-taking, such as adjacency pairs and repairs are well performed. These findings suggest that, despite their limited language production, children at the age of two can actively participate in building and developing conversations with their interlocutors.
17
Rasmussen, Gitte. „Analyzing interaction involving wheelchairs“. Journal of Interactional Research in Communication Disorders 14, Nr. 2 (26.05.2023): 328–55. http://dx.doi.org/10.1558/jircd.25573.
Der volle Inhalt der QuelleAnnotation:
Background: This study shows how the use of wheelchairs due to mobility impairment influences the configuration of interactional spaces and the initiation of conversation. It takes as a case in point the spatial arrangements and interactions between sports students using wheelchairs and their co-participants in a Danish sports high school. Method: Using the framework of research into ethnomethodological conversation analysis (EMCA) in atypical multimodal interaction, this study demonstrates how co-participants with and without impairments consider factors such as the position, size, design, and maneuverability of the wheelchair when they configure interactional spaces and organize conversational beginnings, and how the bodily orientation of the wheelchair user toward a specific physical environment and space is also taken into account. Furthermore, the co-participants’ conversation is adapted to fit these arrangements. The study describes features of spatial configurations that apply irrespective of the presence, type, and degree of disability in speech, language, and communication among the co-participants. The study draws on 10 hours of video recordings. Results and conclusion: The study indicates a need to investigate everyday conversation in its natural surroundings. Detailed descriptions of how co-participants draw upon available material, technological, and bodied ‘modes’ as resources may re-specify our understanding of aspects of conversations when impairments are involved.
18
Kapuskar, Vaibhavi, Sakshi Bobade, Srushti Diwan, Akshata Dholwade, Vaishnavi Kamble und Prof S. R. Gudadhe. „Efficient Chatbot Designing“. International Journal for Research in Applied Science and Engineering Technology 10, Nr. 4 (30.04.2022): 2743–45. http://dx.doi.org/10.22214/ijraset.2022.41889.
Der volle Inhalt der QuelleAnnotation:
Abstract: A conversational agent (chatbot) is a piece of software that is able to communicate with humans using natural language. Modeling conversation is an important task in natural language processing and artificial intelligence (AI). Indeed, ever since the birth of AI, creating a good chatbot remains one of the field’s hardest challenges. While chatbots can be used for various tasks, in general they have to understand users’ utterances and provide responses that are relevant to the problem at hand. In the past, methods for constructing chatbot architectures have relied on hand-written rules and templates or simple statistical methods. With the rise of deep learning these models were quickly replaced by end-to-end trainable neural networks around 2015. More specifically, the recurrent encoder-decoder model [Cho et al., 2014] dominates the task of conversational modeling. This architecture was adapted from the neural machine translation domain, where it performs extremely well. Since then a multitude of variations and features were presented that augment the quality of the conversation that chatbots are capable of the next section of my paper focuses on adapting the very recent Tranformer [Vaswani et al., 2017] model to the chatbot domain, which is currently the state-of-the-art in neural machine translation. I first present my experiments with the vanilla model, using conversations extracted from the Cornell Movie-Dialog Corpus [Danescu-Niculescu-Mizil and Lee, 2011]. Secondly, I augment the model with some of my ideas regarding the issues of encoder-decoder architectures. More specifically, I feed additional features into the model like mood or persona together with the raw conversation data. Finally, I conduct a detailed analysis of how the vanilla model performs on conversational data by comparing it to previous chatbot models and how the additional features, affect the quality of the generated responses
19
Beaver, Ian, und Abdullah Mueen. „On the Care and Feeding of Virtual Assistants: Automating Conversation Review with AI“. AI Magazine 42, Nr. 4 (12.01.2022): 29–42. http://dx.doi.org/10.1609/aimag.v42i4.15101.
Der volle Inhalt der QuelleAnnotation:
With the rise of intelligent virtual assistants (IVAs), there is a necessary rise in human effort to identify conversations containing misunderstood user inputs. These conversations uncover error in natural language understanding and help prioritize improvements to the IVA. As human analysis is time consuming and expensive, prioritizing the conversations where misunderstanding has likely occurred reduces costs and speeds IVA improvement. In addition, less conversations reviewed by humans mean less user data are exposed, increasing privacy. We describe Trace AI, a scalable system for automated conversation review based on the detection of conversational features that can identify potential miscommunications. Trace AI provides IVA designers with suggested actions to correct understanding errors, prioritizes areas of language model repair, and can automate the review of conversations. We discuss the system design and report its performance at identifying errors in IVA understanding compared to that of human reviewers. Trace AI has been commercially deployed for over 4 years and is responsible for significant savings in human annotation costs as well as accelerating the refinement cycle of deployed enterprise IVAs.
20
Beaver, Ian, und Abdullah Mueen. „On the Care and Feeding of Virtual Assistants: Automating Conversation Review with AI“. AI Magazine 42, Nr. 4 (18.01.2022): 29–42. http://dx.doi.org/10.1609/aaai.12024.
Der volle Inhalt der QuelleAnnotation:
With the rise of intelligent virtual assistants (IVAs), there is a necessary rise in human effort to identify conversations containing misunderstood user inputs. These conversations uncover error in natural language understanding and help prioritize improvements to the IVA. As human analysis is time consuming and expensive, prioritizing the conversations where misunderstanding has likely occurred reduces costs and speeds IVA improvement. In addition, less conversations reviewed by humans mean less user data are exposed, increasing privacy. We describe Trace AI, a scalable system for automated conversation review based on the detection of conversational features that can identify potential miscommunications. Trace AI provides IVA designers with suggested actions to correct understanding errors, prioritizes areas of language model repair, and can automate the review of conversations. We discuss the system design and report its performance at identifying errors in IVA understanding compared to that of human reviewers. Trace AI has been commercially deployed for over 4 years and is responsible for significant savings in human annotation costs as well as accelerating the refinement cycle of deployed enterprise IVAs.
21
VanDam, Mark, Lauren Thompson, David Jeson, Aleah Brock, Elizabeth Wilson-Fowler, Sandie Bass-Ringdahl und Paul De Palma. „Preschoolers with hearing loss have asymmetries in the rate of initiating conversations“. Journal of the Acoustical Society of America 153, Nr. 3_supplement (01.03.2023): A291. http://dx.doi.org/10.1121/10.0018887.
Der volle Inhalt der QuelleAnnotation:
Recent work has shown that preschool children initiate more conversations than their mothers and fathers. It has also been shown that boys and girls initiate conversations at about the same rate. It is not known if children with hearing loss initiate conversations at comparable rates to their typically-developing peers, or whether boys and girls with hearing loss differ. In this work, we collected daylong audio recordings from preschoolers with hearing loss using a body-worn audio recorder. We used automatic speech processing routines on the 7600 + hours of audio to identify talkers and conversational turns in their natural family settings. We examined how children with hearing loss initiate conversations compared with their typically-developing peers. We found no difference in rate of conversation initiation by hearing status or sex. We did find that regardless of hearing status or sex, children consistently initiate more conversations with their mothers than with their fathers. Results bear on the role of conversational exchanges, joint attention, and the auditory experiences during speech and language development in children with hearing loss.
22
Geetha, Dr V., Dr C. K. Gomathy, Mr P. V. Sri Ram und Surya Prakash L N. „NOVEL STUDY ON NATURAL LANGUAGE PROCESSING“. INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, Nr. 11 (01.11.2023): 1–11. http://dx.doi.org/10.55041/ijsrem27091.
Der volle Inhalt der QuelleAnnotation:
Natural Language Processing (NLP) is the tech wiz working tirelessly to break down language barriers between us and our devices. It's the reason our smart phone, tablet or laptop understands our voice commands and translates our languages in a second. NLP is like giving machines the ability to comprehend and respond to language nuances, turning our interactions into seamless conversations. Think of it as the digital polyglot that not only reads but truly understands the messages we convey, from the simplest text to the most intricate emotions. From predictive text to chatbots, NLP is the digital linguist enhancing the way we communicate with our devices, making technology feel more like a conversation with a helpful virtual friend. Keywords: seamless conversations, digital polyglot, predictive text, chatbots, digital linguist, technology communication, virtual friend.
23
Nakauchi, Yasushi, Takeshi Takahashi, Piyawat Naphattalung, Takashi Matsubara und Eiichi Kashiwagi. „Commitment-based Natural Language Interface System for Robots“. Journal of Robotics and Mechatronics 14, Nr. 5 (20.10.2002): 490–96. http://dx.doi.org/10.20965/jrm.2002.p0490.
Der volle Inhalt der QuelleAnnotation:
In this paper, we first discuss how the commitment in human-robot natural language conversation is important and the lack of the commitment leads to breakdowns in conversation. Then, we propose a human-robot conversation model, which takes the breakdown into consideration. We implemented a natural language interface system of a mobile robot, based on the proposed conversation model. Then, we conducted experiments with subjects and confirmed that the proposed interface system provides more natural conversation between human and robot with fewer breakdowns.
24
Simmons-Mackie, Nina N., und Jack S. Damico. „The Contribution of Discourse Markers to Communicative Competence in Aphasia“. American Journal of Speech-Language Pathology 5, Nr. 1 (Februar 1996): 37–43. http://dx.doi.org/10.1044/1058-0360.0501.37.
Der volle Inhalt der QuelleAnnotation:
Discourse markers, expressions used to organize conversational interaction, are widely used by speakers in social conversation. An ethnographic investigation of compensatory strategies employed in natural communication by two aphasic subjects revealed a variety of behaviors fulfilling the requirements of discourse markers. The role of discourse markers as compensatory strategies to promote conversation in aphasia is discussed, with descriptive examples drawn from the ethnographic study.
25
Mathewson, Kory, und Piotr Mirowski. „Improvised Theatre Alongside Artificial Intelligences“. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 13, Nr. 1 (25.06.2021): 66–72. http://dx.doi.org/10.1609/aiide.v13i1.12926.
Der volle Inhalt der QuelleAnnotation:
This study presents the first report of Artificial Improvisation, or improvisational theatre performed live, on-stage, alongside an artificial intelligence-based improvisational performer. The Artificial Improvisor is a form of artificial conversational agent, or chatbot, focused on open domain dialogue and collaborative narrative generation. Using state-of-the-art machine learning techniques spanning from natural language processing and speech recognition to reinforcement and deep learning, these chatbots have become more lifelike and harder to discern from humans. Recent work in conversational agents has been focused on goal-directed dialogue focused on closed domains such as appointment setting, bank information requests, question-answering, and movie discussion. Natural human conversations are seldom limited in scope and jump from topic to topic, they are laced with metaphor and subtext and face-to-face communication is supplemented with non-verbal cues. Live improvised performance takes natural conversation one step further with multiple actors performing in front of an audience. In improvisation the topic of the conversation is often given by the audience several times during the performance. These suggestions inspire actors to perform novel, unique, and engaging scenes. During each scene, actors must make rapid fire decisions to collaboratively generate coherent narratives. We have embarked on a journey to perform live improvised comedy alongside artificial intelligence systems. We introduce Pyggy and A.L.Ex. (Artificial Language Experiment), the first two Artificial Improvisors, each with a unique composition and embodiment. This work highlights research and development, successes and failures along the way, celebrates collaborations enabling progress, and presents discussions for future work in the space of artificial improvisation.
26
Goh, Ong Sing, Chun Che Fung, Kok Wai Wong und Arnold Depickere. „Embodied Conversational Agents for H5N1 Pandemic Crisis“. Journal of Advanced Computational Intelligence and Intelligent Informatics 11, Nr. 3 (20.03.2007): 282–88. http://dx.doi.org/10.20965/jaciii.2007.p0282.
Der volle Inhalt der QuelleAnnotation:
This paper presents a novel framework for modeling embodied conversational agent for crisis communication focusing on the H5N1 pandemic crisis. Our system aims to cope with the most challenging issue on the maintenance of an engaging while convincing conversation. What primarily distinguishes our system from other conversational agent systems is that the human-computer conversation takes place within the context of H5N1 pandemic crisis. A Crisis Communication Network, called CCNet, is established based on a novel algorithm incorporating natural language query and embodied conversation agent simultaneously. Another significant contribution of our work is the development of a Automated Knowledge Extraction Agent (AKEA) to capitalize on the tremendous amount of data that is now available online to support our experiments. What makes our system differs from typical conversational agents is the attempt to move away from strictly task-oriented dialogue.
27
Beaver, Ian, und Abdullah Mueen. „Automated Conversation Review to Surface Virtual Assistant Misunderstandings: Reducing Cost and Increasing Privacy“. Proceedings of the AAAI Conference on Artificial Intelligence 34, Nr. 08 (03.04.2020): 13140–47. http://dx.doi.org/10.1609/aaai.v34i08.7017.
Der volle Inhalt der QuelleAnnotation:
With the rise of Intelligent Virtual Assistants (IVAs), there is a necessary rise in human effort to identify conversations containing misunderstood user inputs. These conversations uncover error in natural language understanding and help prioritize and expedite improvements to the IVA. As human reviewer time is valuable and manual analysis is time consuming, prioritizing the conversations where misunderstanding has likely occurred reduces costs and speeds improvement. In addition, less conversations reviewed by humans mean less user data is exposed, increasing privacy. We present a scalable system for automated conversation review that can identify potential miscommunications. Our system provides IVA designers with suggested actions to fix errors in IVA understanding, prioritizes areas of language model repair, and automates the review of conversations where desired.Verint - Next IT builds IVAs on behalf of other companies and organizations, and therefore analyzes large volumes of conversational data. Our review system has been in production for over three years and saves our company roughly $1.5 million in annotation costs yearly, as well as shortened the refinement cycle of production IVAs. In this paper, the system design is discussed and performance in identifying errors in IVA understanding is compared to that of human reviewers.
28
Oktarini, Kadek Ratih Dwi. „Are You Flirting, Objectifying or What? a Conversation Analysis of “you’re very sexy” Conversational Turn“. SOSHUM : Jurnal Sosial dan Humaniora 10, Nr. 3 (28.11.2020): 294–308. http://dx.doi.org/10.31940/soshum.v10i3.1972.
Der volle Inhalt der QuelleAnnotation:
Intent identification is one of the most critical components in conversational agent design. Conversational agent “is any dialogue system that not only conducts natural language processing but also responds automatically using human language.” (Conversational Agent, 2019). The crux of designing human-like conversational agent is to mimic how human understands another human and then responds “naturally”. The current study attempts to answer the fundamental question: how to model human processes of understanding another human? In order to answer that question, it starts from exploring some basic concepts relevant to intent identification from Conversation Analysis (CA). CA is a mature field that studies authentic human interaction. The basic concepts from CA are then synthesised into a model that potentially fit to existing framework and paradigm in conversational agent design, i.e. Natural Conversation Framework (NCF) and Intent-Entity-Context-Response (IECR) paradigm. Instead of using a made-up sentence, the model is then tested to an authentic conversational turn seksi sekali dirimu ‘you’re very sexy’. The test shows that the model is able to detect several possible intents contain in this authentic conversational turn. The model is also able to handle Conversational Indonesian and multi-modality. Considering the versatility of Conversation Analysis, in all likelihood the model will be able to handle any language and all kinds of modalities. Future study can be done to analyse more Conversational Indonesian data (to develop library of intent for Conversational Indonesian Language), as well as conversational data from different languages and conversational data containing diverse modalities.
29
Winarti, Oktifani. „Types of messages used by mothers to communicate the children: conversation analysis“. Jurnal Studi Komunikasi (Indonesian Journal of Communications Studies) 7, Nr. 1 (01.04.2023): 285–96. http://dx.doi.org/10.25139/jsk.v7i1.6154.
Der volle Inhalt der QuelleAnnotation:
Using Conversation Analysis, this paper explores the interaction between a mother and their children while giving morality messages. Conversation Analysis breaks down every interaction between a mother and their children to understand the success of interaction for a mother in delivering moral lessons to her children. By using a natural-setting audio recording and exporting the conversation through excerpts of conversations, this paper reveals three interesting findings from their interaction and turn-taking through varieties of turn-design sequences. The findings of this research show there are three ways of interaction used by mothers: 1) future forecasting, 2) authority-evoking, and 3) self-disclosing.
30
Bardovi-Harling, K., B. A. S. Hartford, R. Mahan-Taylor, M. J. Morgan und D. W. Reynolds. „Developing pragmatic awareness: closing the conversation“. ELT Journal 45, Nr. 1 (01.01.1991): 4–15. http://dx.doi.org/10.1093/elt/45.1.4.
Der volle Inhalt der QuelleAnnotation:
Abstract Many commercially available English-language materials do not provide natural, or even pragmatically appropriate, conversational models for learners. This paper argues for increasing the role of pragmastics in English-language instruction. Classroom teachers can integrate pragmatics into the language curriculum by drawing on natural conversations, students' observations, and incomplete dialogues in textbooks. The paper provides guide-lines for pragmatically-centred lessons, as well as examples of specific activities, using closings in American English to illustrate these examples.
31
Wei, Jing, Sungdong Kim, Hyunhoon Jung und Young-Ho Kim. „Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data“. Proceedings of the ACM on Human-Computer Interaction 8, CSCW1 (17.04.2024): 1–35. http://dx.doi.org/10.1145/3637364.
Der volle Inhalt der QuelleAnnotation:
Large language models (LLMs) provide a new way to build chatbots by accepting natural language prompts. Yet, it is unclear how to design prompts to power chatbots to carry on naturalistic conversations while pursuing a given goal such as collecting self-report data from users. We explore what design factors of prompts can help steer chatbots to talk naturally and collect data reliably. To this aim, we formulated four prompt designs with different structures and personas. Through an online study (N = 48) where participants conversed with chatbots driven by different designs of prompts, we assessed how prompt designs and conversation topics affected the conversation flows and users' perceptions of chatbots. Our chatbots covered 79% of the desired information slots during conversations, and the designs of prompts and topics significantly influenced the conversation flows and the data collection performance. We discuss the opportunities and challenges of building chatbots with LLMs.
32
B, Mr DHANUSH. „CHATBOT USING LARGE LANGUAGE MODEL“. INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, Nr. 05 (14.05.2024): 1–5. http://dx.doi.org/10.55041/ijsrem34001.
Der volle Inhalt der QuelleAnnotation:
The concept of Natural Language Processing has seen a remarkable advancement in the recent years. This remarkable advancement was particularly with the development of Large Language Models (LLM). Large Language Models are used to develop a human like conversations. This LLM is a part of Natural Language Processing which focuses on enabling computers to understand, interpret, and generate human language. The existing system of chatbots does not generate human like responses. The proposed system of chatbots uses the power of Large Language Models to generate more human like responses, providing the conversation in a natural way. By genereating human like respones, it will be in a natural way for the user. To enhance user experience, the chatbot uses a dynamic learning mechanism, by which it continuously adapt to user preferences and evolving conversational patterns. This system uses feedbacks from the users to refine its responses everytime.Moreover, the chatbot is designed with a multi-turn conversational context awareness, allowing it to maintain coherence and relevance throughout extended dialogues.The effectiveness of the proposed chatbot is evaluated through user testing, comparing its performance against traditional rule-based chatbots and existing conversational agents. This report explains about the usage of Large Language Models in the design and implementation of conversational chatbots. The outcomes of this research contribute to the advancement of intelligent chatbot systems, demonstrating the potential of large language models to significantly enhance conversational AI applications.
33
Du, Lingxiao. „Query-Based Dialogue Summarization Using BART“. Applied and Computational Engineering 29, Nr. 1 (22.01.2024): 160–66. http://dx.doi.org/10.54254/2755-2721/29/20231149.
Der volle Inhalt der QuelleAnnotation:
Conversation summarisation is the transformation of long conversational texts into concise and accurate summaries, the importance of which lies in improving the user experience and information filtering. As an important natural language processing task, conversation summarisation can provide concise and accurate information and avoid repetition and redundancy. In the dialogue summarisation task, pre-trained language models can be used to summarise long conversations and generate concise and accurate summaries. The aim of this paper is to investigate the possibility of using bidirectional and auto-regressive transformer models for dialogue summarisation tasks. In our experiments, we analysed the characteristics of the Query-based Multi-domain Meeting Summarization (QMsum) dialogue summarisation dataset, proposed a dialogue summarisation model based on the Bidirectional and Auto-Regressive Transformer model, and designed evaluation experiments to compare its performance with other methods in the dialogue summarisation task. The experimental results show that the results of this thesis are important for facilitating the development of dialogue summarisation tasks and the application of the Bidirectional and Auto-Regressive Transformer model.
34
Wang, Xiaoyang, Chen Li, Jianqiao Zhao und Dong Yu. „NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation“. Proceedings of the AAAI Conference on Artificial Intelligence 35, Nr. 16 (18.05.2021): 14006–14. http://dx.doi.org/10.1609/aaai.v35i16.17649.
Der volle Inhalt der QuelleAnnotation:
In this paper, we propose a Chinese multi-turn topic-driven conversation dataset, NaturalConv, which allows the participants to chat anything they want as long as any element from the topic is mentioned and the topic shift is smooth. Our corpus contains 19.9K conversations from six domains, and 400K utterances with an average turn number of 20.1. These conversations contain in-depth discussions on related topics or widely natural transition between multiple topics. We believe either way is normal for human conversation. To facilitate the research on this corpus, we provide results of several benchmark models. Comparative results show that for this dataset, our current models are not able to provide significant improvement by introducing background knowledge/topic. Therefore, the proposed dataset should be a good benchmark for further research to evaluate the validity and naturalness of multi-turn conversation systems. Our dataset is available at https://ai.tencent.com/ailab/nlp/dialogue/#datasets.
35
Goar, Vishal, Nagendra Singh Yadav und Pallavi Singh Yadav. „Conversational AI for Natural Language Processing: An Review of ChatGPT“. International Journal on Recent and Innovation Trends in Computing and Communication 11, Nr. 3s (11.03.2023): 109–17. http://dx.doi.org/10.17762/ijritcc.v11i3s.6161.
Der volle Inhalt der QuelleAnnotation:
ChatGPT is a conversational artificial intelligence model developed by OpenAI, which was introduced in 2019. It employs a transformer-based neural mesh to produce human being responses in real-time, allowing for natural language conversations with a machine. ChatGPT is instructed on huge quantities of data captured using the internet, making it knowledgeable in an extensive span of topics, from news & entertainment to politics and sports. This allows it to generate contextually relevant responses to questions and statements, making the conversation seem more lifelike. The model can be used in various applications, including customer service, personal assistants, and virtual assistants. ChatGPT has also shown promising results in generating creative content, such as jokes and poetry, showcasing its versatility and potential for future applications.This paper provides a comprehensive review of the existing literature on ChatGPT, highlighting its key advantages, such as improved accuracy and flexibility compared to traditional NLP tools, as well as its limitations and the need for further research to address potential ethical concerns. The review also highlights the potential for ChatGPT to be used in NLP applications, including question-answering and dialogue generation, and highlights the need for further research and development in these areas.
36
Norrick, Neal R. „Swearing in literary prose fiction and conversational narrative“. Narrative Inquiry 22, Nr. 1 (31.12.2012): 24–49. http://dx.doi.org/10.1075/ni.22.1.03nor.
Der volle Inhalt der QuelleAnnotation:
This article compares swearing in novels with swearing in everyday talk based on a representative sample of British and American prose fiction and a several large corpora of natural conversation. Swearing allegedly makes fictional dialogue more realistic, but up till now no one has attempted a systematic comparison of fictional and natural conversational swearing. Fiction writers incorporate swearing into their dialogue to delineate characters and to signal emotions, sometimes setting it off from non-swearing talk and commenting on it in various ways. Traditionally, the author’s own voice contained no swearing. By contrast, in conversational narratives, tellers use swearing to obtain the floor, to evaluate action, to mark climaxes and closings, in addition to portraying their characters as swearing. Moreover, in conversation, tellers may hear their listeners swearing along with them, not only to support and evaluate, but also to oppose and even complain about their telling performance.
37
Elvir, Miguel, Avelino J. Gonzalez, Christopher Walls und Bryan Wilder. „Remembering a Conversation – A Conversational Memory Architecture for Embodied Conversational Agents“. Journal of Intelligent Systems 26, Nr. 1 (01.01.2017): 1–21. http://dx.doi.org/10.1515/jisys-2015-0094.
Der volle Inhalt der QuelleAnnotation:
AbstractThis paper addresses the role of conversational memory in Embodied Conversational Agents (ECAs). It describes an investigation into developing such a memory architecture and integrating it into an ECA. ECAs are virtual agents whose purpose is to engage in conversations with human users, typically through natural language speech. While several works in the literature seek to produce viable ECA dialog architectures, only a few authors have addressed the episodic memory architectures in conversational agents and their role in enhancing their intelligence. In this work, we propose, implement, and test a unified episodic memory architecture for ECAs. We describe a process that determines the prevalent contexts in the conversations obtained from the interactions. The process presented demonstrates the use of multiple techniques to extract and store relevant snippets from long conversations, most of whose contents are unremarkable and need not be remembered. The mechanisms used to store, retrieve, and recall episodes from previous conversations are presented and discussed. Finally, we test our episodic memory architecture to assess its effectiveness. The results indicate moderate success in some aspects of the memory-enhanced ECAs, as well as some work still to be done in other aspects.
38
Koegel, Lynn Kern, Zak Koplen, Brittany Koegel und Robert L. Koegel. „Using a Question Bank Intervention to Improve Socially Initiated Questions in Adolescents and Adults With Autism“. Journal of Speech, Language, and Hearing Research 64, Nr. 4 (14.04.2021): 1331–39. http://dx.doi.org/10.1044/2021_jslhr-20-00534.
Der volle Inhalt der QuelleAnnotation:
Purpose Individuals with autism spectrum disorder (ASD) often have difficulty asking questions during social conversation, which can negatively impact their interactions with peers. The purpose of this study was to assess whether a question bank intervention would be effective in improving question asking during social conversation. Method In the context of a multiple-baseline experimental design, we implemented an intervention using prepractice with question banks designed to increase the number and diversity of questions asked by adolescents and adults with ASD during social conversations with their peers. Results Following intervention, all participants improved their use of questions in natural settings with their neurotypical peers. Generalization to novel questions occurred, and gains were maintained at follow-up. Finally, supplemental measures of social validity showed that similarly aged neurotypical peers who were naïve to the experimental hypothesis rated two of the three participants with higher social desirability following intervention. Conclusion Individuals with ASD can improve their appropriate question asking during social conversation using a brief question bank intervention with generalization to their peers in natural settings.
39
MACBETH, DOUGLAS. „The relevance of repair for classroom correction“. Language in Society 33, Nr. 5 (November 2004): 703–36. http://dx.doi.org/10.1017/s0047404504045038.
Der volle Inhalt der QuelleAnnotation:
This article attempts to align a familiar task of classroom teaching, eliciting from students correct answers about their lessons, with a major organizational domain in studies of natural conversation, that of conversational repair. Numerous studies have analyzed correction sequences in classroom discourse, and our discussion pays special attention to McHoul's (1990) treatment of “repair in classroom talk.” McHoul directly measures the findings on repair in studies of natural conversation to the regularities of correction sequences in classroom lessons. It is argued, contra McHoul, that repair is a different, and prior, order of discursive work, and one that premises the very possibility of classroom correction. Further, the difference may have wider relevance for understanding repair and correction as “co-operating” organizations of talk-in-interaction more generally.
40
Omarov, Batyrkhan, Sergazi Narynov, Zhandos Zhumanov, Elmira Alzhanova, Aidana Gumar und Mariyam Khassanova. „Artificial intelligence enabled conversational agent for mental healthcare“. International journal of health sciences 6, Nr. 3 (05.10.2022): 1544–55. http://dx.doi.org/10.53730/ijhs.v6n3.13239.
Der volle Inhalt der QuelleAnnotation:
Conversational agents are a software program that can converse with users in the manner of a real-world conversation. Artificial intelligence (AI) is not complete without conversation modeling. The most difficult artificial intelligence endeavor since its start has been developing an effective chatbot application. Despite chatbots may do a variety of tasks, their main duty is to accurately understand human speech and respond appropriately. Previously, manual patterns and instructions or simple statistical methods were used to create chatbots architectures. Due to its improved capacity for training, end-to-end AI has replaced these models since 2015. The most popular technique for conversation simulation at the moment is the encoder-decoder recurrent neural network (RNN). The realm of language comprehension served as inspiration for this design. Until recently, a number of additions and changes dramatically enhanced chatbot conversational abilities. In this paper, we outline our research results into creating an interactive digital chatbot that may provide patients with psychological assistance. To build and train the chatbot, we used resources such Rasa Natural Language Processing (NLU) technology, which employs natural language processing (NLP) methods. The results of the investigation showed that selecting proper responses while conversing with patients had a more than 70% predictive performance.
41
Moore, Robert J., Sungeun An und Olivia H. Marrese. „Understanding is a Two-Way Street: User-Initiated Repair on Agent Responses and Hearing in Conversational Interfaces“. Proceedings of the ACM on Human-Computer Interaction 8, CSCW1 (17.04.2024): 1–26. http://dx.doi.org/10.1145/3641026.
Der volle Inhalt der QuelleAnnotation:
Although methods for repairing prior turns in natural conversation are critical for enabling mutual understanding, or successful communication, these methods are seldom built into conversational user interfaces systematically. Chatbots and voice assistants tend to ask users to paraphrase what they said if it was not understood, but users cannot do the same if they encounter trouble in understanding what the agent said. Understanding is a one-way street in most (intent-based) conversation-like interfaces. An exception to this is Moore and Arar (2019), who demonstrate nine types of user-initiated repair on agent responses that are common in natural conversation and who have shown that users will employ these repair features correctly in text-based interfaces if taught. In this small-scale study, we test these user-initiated repairs (in second position) in a voice-based interface. With understanding-oriented repairs, we found that participants employed them much the same way in text and voice. In addition, we examine some hearing- and speaking-oriented repairs that emerged from the use of our novel multi-modal interface. We found that participants used them to manage troubles specific to the voice modality. Analysis of user logs and transcripts suggests that user-initiated repair features are valuable components of conversational interfaces.
42
Lin, Dongding, Jian Wang und Wenjie Li. „COLA: Improving Conversational Recommender Systems by Collaborative Augmentation“. Proceedings of the AAAI Conference on Artificial Intelligence 37, Nr. 4 (26.06.2023): 4462–70. http://dx.doi.org/10.1609/aaai.v37i4.25567.
Der volle Inhalt der QuelleAnnotation:
Conversational recommender systems (CRS) aim to employ natural language conversations to suggest suitable products to users. Understanding user preferences for prospective items and learning efficient item representations are crucial for CRS. Despite various attempts, earlier studies mostly learned item representations based on individual conversations, ignoring item popularity embodied among all others. Besides, they still need support in efficiently capturing user preferences since the information reflected in a single conversation is limited. Inspired by collaborative filtering, we propose a collaborative augmentation (COLA) method to simultaneously improve both item representation learning and user preference modeling to address these issues. We construct an interactive user-item graph from all conversations, which augments item representations with user-aware information, i.e., item popularity. To improve user preference modeling, we retrieve similar conversations from the training corpus, where the involved items and attributes that reflect the user's potential interests are used to augment the user representation through gate control. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our method. Our code and data are available at https://github.com/DongdingLin/COLA.
43
Turner, Elise H., und Richard E. Cullingford. „Using conversation MOPs in natural language interfaces“. Discourse Processes 12, Nr. 1 (Januar 1989): 63–90. http://dx.doi.org/10.1080/01638538909544719.
Der volle Inhalt der Quelle
44
Basso, Anna. „“Natural” conversation: A treatment for severe aphasia“. Aphasiology 24, Nr. 4 (16.09.2009): 466–79. http://dx.doi.org/10.1080/02687030802714165.
Der volle Inhalt der Quelle
45
Blonder, L. X., A. F. Burns, D. Bowers, R. W. Moore und K. M. Heilman. „Right Hemisphere Facial Expressivity During Natural Conversation“. Brain and Cognition 21, Nr. 1 (Januar 1993): 44–56. http://dx.doi.org/10.1006/brcg.1993.1003.
Der volle Inhalt der Quelle
46
Nan, Guiyu. „Analysis of Korean Speaking Patterns: Through the Drama [God of Study]“. Korean Society of Culture and Convergence 44, Nr. 8 (31.08.2022): 59–69. http://dx.doi.org/10.33645/cnc.2022.8.44.8.59.
Der volle Inhalt der QuelleAnnotation:
The purpose of this study is to examine the pattern of having it in Korean conversation through conversation analysis in the drama [God of Study] and the theory of horse's turn-taking. In this study, the method of having a turn of speech was first classified into two aspects: regular turn of speech and irregular turn of speech, and then regular turn of speech and irregular turn of speech were classified into verbal and nonverbal elements. Through this analysis, in the conclusion of this study, I tried to find a strategy for taking turns in Korean conversation. This study can serve as a basic study to guide foreign learners on the aspect of speaking in Korean. In addition, it is expected that foreign learners learning Korean will be able to effectively bring the turn of words while having daily conversations and continue a natural conversation through the speaking-to-talk strategy presented in this study, which is expected to be of some help.
47
Farinde, Raifu Olanrewaju, Happy Ojo Omolaiye und Muibat Abiola Farinde. „A Pragmatic Analysis of Cultural Influence on Politeness Markers in the Yoruba Context“. Theory and Practice in Language Studies 13, Nr. 4 (01.04.2023): 822–29. http://dx.doi.org/10.17507/tpls.1304.02.
Der volle Inhalt der QuelleAnnotation:
Culture plays a significant role in language use. It is a parameter for measuring communicative competence of a language user. Thus, the use of language is the function of the culture that owns the language. This study is predicated on Grice’s (1975) conversational implicature theory. Data was got from recorded conversations in different natural settings in Ondo West Local Government Area of Ondo State, Nigeria. The focus of the study is on politeness markers in “leader-follower”, “husband-wife”, “father-son”, “buyer-seller”, “friend-friend” and “elder brother-younger brother” conversations. Ten tape recordings were made out of which, seven were used for analysis. The pragmatic analysis of cultural influence on politeness has revealed the influence of culture on politeness markers in the Yoruba context. The study has also revealed the persuasive approach employed by the interlocutors to maintain and sustain conversation. It has been discovered that culture has conditioned the husband to assert while the wife is culture-bound to obey the assertion of her husband. This paper, therefore, recommends that language users should be exposed to the culture of the language being used as it will broaden their knowledge on how to sustain and maintain face saving act in a conversation. The knowledge of culture will definitely enhance the communicative competence of language users.
48
이순형. „Grammatical Syllabus of Text Conversation Seen from Feature of Natural Conversation－Through the Comparison Analysis with the Natural“. Journal of Japanese Language and Literature 76, Nr. 1 (Februar 2011): 331–50. http://dx.doi.org/10.17003/jllak.2011.76.1.331.
Der volle Inhalt der Quelle
49
Ismiati, Ismiati. „ANALYZING IMPLICATURES IN TALIWANG DIALECT“. Journal of Languages and Language Teaching 9, Nr. 4 (25.10.2021): 432. http://dx.doi.org/10.33394/jollt.v9i4.4215.
Der volle Inhalt der QuelleAnnotation:
This study aims to analyze the types of implicature and flouting maxims and the reasons for doing the flouting in Taliwang Dialect. It applied the descriptive method with a qualitative approach. Data was collected by recording natural conversations among the natives of Taliwang Dialect. It was found two types of implicature, namely, Generalized Conversational Implicature (GCI) and Particularized Conversational Implicatures (PCI). In GCI, the speaker and interlocutor could easily understand the conveyed utterances because they mostly used general statements which are commonly spoken in the Taliwang dialect. In PCI, both speaker and the interlocutor needed a particular knowledge to understand each other because of the flouting maxim. Some speakers or hearers in PCI often break the maxim in a conversation due to some reasons such as accepting untrue or lie information, receiving more information than the needed information, getting irrelevant information and having unclear or ambiguous information.
50
Gupta, Vibhuti, und Megha Gupta. „A Modern Tool of Conversation: Chatbot“. Journal of Ubiquitous Computing and Communication Technologies 4, Nr. 3 (03.09.2022): 138–49. http://dx.doi.org/10.36548/jucct.2022.3.002.
Der volle Inhalt der QuelleAnnotation:
A chatbot is a work of artificial intelligence technology that simulates a conversation (or chat) in natural language with a user via messaging applications, internet sites, smartphone apps, or the telephone. Chatbots are used in a range of conversation systems for a variety of purposes, including customer assistance, request processing, and information acquisition. Chatbots have been around for quite some time, but it has only been in the recent past few years that they have seen a significant uptick in popularity among consumers and companies. This change in the perspective of chatbots and conversational interfaces was heavily impacted by the advancements in artificial intelligence and machine learning, as well as by the expanding usage of messaging app technologies. This study offers a comprehensive analysis of the conversational tool known as chatbots, which emerged in the contemporary era. This paper also discusses how this tool is expanding its root in the life of human beings as well as the pros-cons that will be generated by the chatbots.