Tesis sobre el tema "Chatbot dialogue"

A chatbot is a computer program that engages in written or spoken conversation with a human user. This project aims to investigate the possibility of training a chatbot in using movie dialogue in generating the response. Movie dialogue can be found in both movie scripts as well as subtitles, though using subtitles is much easier as they follow a special formatting. Using one subtitle as a response to each word found in the preceding subtitle, the implemented chatbot links together subtitles. The responses are stored in a frequency distribution table that maps each word to all responses found. Though the responses generated by the chatbot were not desirable, the responsese tmost often contained responses which would be more fitting. The result drawn from hisis that ,with further work and improvement,the chatbot could perform acceptably

Les Systèmes de Dialogue (ou simplement chatbots) sont très demandés de nos jours. Ils permettent de comprendre les besoins des utilisateurs (ou intentions des utilisateurs), exprimés en langage naturel, et de répondre à ces intentions en invoquant les APIs (Interfaces de Programmation d’Application) appropriées. Les chatbots sont connus pour leur interface facile à utiliser et ils ne nécessitent que l'une des capacités les plus innées des humains qui est l'utilisation du langage naturel. L'amélioration continue de l'Intelligence Artificielle (IA), du Traitement du Langage Naturel (NLP) et du nombre incalculable de dispositifs permettent d'effectuer des tâches réelles (par exemple, faire une réservation) en utilisant des interactions basées sur le langage naturel entre les utilisateurs et un grand nombre de services.Néanmoins, le développement de chatbots est encore à un stade préliminaire, avec plusieurs défis théoriques et techniques non résolus découlant de (i) la variations d'énoncés dans les interactions humain-chatbot en libre échange et (ii) du grand nombre de services logiciels potentiellement inconnus au moment du développement. Les conversations en langage naturel des personnes peuvent être riches, potentiellement ambiguës et exprimer des intentions complexes et dépendantes du contexte. Les techniques traditionnelles de modélisation et d'orchestration de processus et de composition de services sont limitées pour soutenir de telles conversations car elles supposent généralement une attente a priori de quelles informations et applications seront accédées et comment les utilisateurs exploreront ces sources et services. Limiter les conversations à un modèle de processus signifie que nous ne pouvons soutenir qu'une petite fraction de conversations possibles. Bien que les avancées existantes dans les techniques de NLP et d'apprentissage automatique (ML) automatisent diverses tâches telles que la reconnaissance d'intention, la synthèse d'appels API pour prendre en charge une large gamme d'intentions d'utilisateurs potentiellement complexes est encore largement un processus manuel et coûteux.Ce projet de thèse vise à faire avancer la compréhension fondamentale de l'ingénierie des services cognitifs. Dans cette thèse, nous contribuons à des abstractions et des techniques novatrices axées sur la synthèse d'appels API pour soutenir une large gamme d'intentions d'utilisateurs potentiellement complexes. Nous proposons des techniques réutilisables et extensibles pour reconnaître et réaliser des intentions complexes lors des interactions entre humains, chatbots et services. Ces abstractions et techniques visent à débloquer l'intégration transparente et évolutive de conversations basées sur le langage naturel avec des services activés par logiciel
Dialogue Systems (or simply chatbots) are in very high demand these days. They enable the understanding of user needs (or user intents), expressed in natural language, and on fulfilling such intents by invoking the appropriate back-end APIs (Application Programming Interfaces). Chatbots are famed for their easy-to-use interface and gentle learning curve (it only requires one of humans' most innate ability, the use of natural language). The continuous improvement in Artificial Intelligence (AI), Natural Language Processing (NLP), and the countless number of devices allow performing real-world tasks (e.g., making a reservation) by using natural language-based interactions between users and a large number of software enabled services.Nonetheless, chatbot development is still in its preliminary stage, and there are several theoretical and technical challenges that need to be addressed. One of the challenges stems from the wide range of utterance variations in open-end human-chatbot interactions. Additionally, there is a vast space of software services that may be unknown at development time. Natural human conversations can be rich, potentially ambiguous, and express complex and context-dependent intents. Traditional business process and service composition modeling and orchestration techniques are limited to support such conversations because they usually assume a priori expectation of what information and applications will be accessed and how users will explore these sources and services. Limiting conversations to a process model means that we can only support a small fraction of possible conversations. While existing advances in NLP and Machine Learning (ML) techniques automate various tasks such as intent recognition, the synthesis of API calls to support a broad range of potentially complex user intents is still largely a manual, ad-hoc and costly process.This thesis project aims at advancing the fundamental understanding of cognitive services engineering. In this thesis we contribute novel abstractions and techniques focusing on the synthesis of API calls to support a broad range of potentially complex user intents. We propose reusable and extensible techniques to recognize and realize complex intents during humans-chatbots-services interactions. These abstractions and techniques seek to unlock the seamless and scalable integration of natural language-based conversations with software-enabled services

Motivée par le gain en popularité des chatbots prenant le rôle de conseillers sur les sites Web des entreprises, cette thèse s'attaque au problème de la détection des problèmes d’interaction entre un conseiller virtuel et ses utilisateurs sous l'angle de l'analyse des opinions et des émotions dans les textes. Cette thèse s’est déroulée dans le cadre d’une application concrète pour l’entreprise EDF et s'est appuyée sur le corpus du chatbot d'EDF. Ce corpus regroupe des expressions spontanées et riches, collectées dans les conditions écologiques (parfois appelées « in-the-wild »), difficiles à analyser de façon automatique, et encore peu étudiées. Nous proposons une typologie des problèmes d’interaction et faisons annoter une partie du corpus selon cette typologie, annotation dont une partie servira à l’évaluation du système. Le système de Détection Automatique des Problèmes d’Interaction (DAPI) développé lors de cette thèse est un système hybride qui allie l’approche symbolique et l’apprentissage non supervisé de représentation sémantique par plongements lexicaux (word embeddings). Le système DAPI a pour vocation d'être directement connecté au chatbot et de détecter des problèmes d’interaction en ligne, dès la réception d’un énoncé utilisateur. L'originalité de la méthode proposée repose sur : i) la prise en compte de l'historique du dialogue; ii) la modélisation des problèmes d’interaction en tant qu'expressions des opinions et des phénomènes reliés aux opinions spontanées de l'utilisateur vis-à-vis de l'interaction; iii) l'intégration des spécificités du langage web et « in-the-wild » comme des indices linguistiques pour les règles linguistiques; iv) recours aux plongements lexicaux de mots (word2vec) appris sur le grand corpus du chatbot non étiqueté afin de modéliser des similarités sémantiques. Les résultats obtenus sont très encourageants compte tenu de la complexité des données : F-score = 74,3%
This PHD thesis is motivated by the growing popularity of chatbots acting as advisors on corporate websites. This research addresses the detection of the interaction problems between a virtual advisor and its users from the angle of opinion and emotion analysis in the texts. The present study takes place in the concrete application context of a French energy supplier EDF, using EDF chatbot corpus. This corpus gathers spontaneous and rich expressions, collected in "in-the-wild" conditions, difficult to analyze automatically, and still little studied. We propose a typology of interaction problems and annotate a part of the corpus according to this typology. A part of created annotation is used to evaluate the system. The system named DAPI (automatic detection of interaction problems) developed during this thesis is a hybrid system that combines the symbolic approach and the unsupervised learning of semantic representation (word embeddings). The purpose of the DAPI system is to be directly connected to the chatbot and to detect online interaction problems as soon as a user statement is received. The originality of the proposed method is based on : i) taking into account the history of the dialogue ; ii) the modeling of interaction problems as the expressions of user spontaneous opinion or emotion towards the interaction ; iii) the integration of the web-chat and in-the-wild language specificities as linguistic cues for linguistic rules ; iv) use of lexical word embedding (word2vec) learned on the large untagged chatbot corpus to model semantic similarities. The results obtained are very encouraging considering the complexity of the data : F-score = 74.3%

Chatbots are becoming more common in modern society, but there are almost no studies that explore both the differences and causes that divides human communication from communication with a chatbot. The aim of this thesis was to explore different recipient design people take when communicating with a human and a chatbot. A chatbot was built and an experiment was conducted that measured the performance and experience of the participants. A thematic analysis then found out causes for these experiences. The study focused on finding new differences in addition to exploring people’s boredom, frustration, understanding, repetition, and performance in a task. The study found differences and causes in people’s recipient design when communicating with a human compared to a chatbot, as well as differences in the performance of a task. Hopefully, this will help future research figure out solutions for the differences found.

Despite being explored and constantly improved through the years, onboarding of new hires in corporate organizations has remained a challenge. Many of the issues can be linked to a lack of communication between the organization and the new employee, as well as the common nature of these environments where information is spread across job titles and sources. This thesis discusses the feasibility of implementing a basic chatbot that will allow new hires to ask questions and request varied information at all times, using an interface such as a messaging app. This research explores the way chatbots should be designed in order to be effective, reliable and enjoyable from a user experience perspective. The chatbot was developed using the Chatfuel platform and tested by new employees at a corporate environment. The users were requested to explore the chatbot freely and then asked to answer a survey. The interactions were also recorded and analyzed from in both qualitative and quantitative ways (chat logs and analytics). The study proves that an onboarding chatbot is a useful tool for new hires and can be used as a communication facilitator between the organization and the new hires during the first weeks of employment, and also after that, serving as an information source and a broadcasting method. The chatbot gives the new hires an accessible source of information that helps on the process of getting to speed, and enables a positive experience that increases familiarity in the new workplace.

Automatisering av kundtjänster genom implementering av chatbotar blir allt vanligare för att kunna erbjuda kunder en mer tillgänglig och effektiv service. Vid implementering av chatbotar i kundtjänster lämnas den mänskliga kontrollen och kundens upplevelse delvis över till ett digitalt system, vilket ställer krav på utformning av chatbotars dialoger. Syftet med arbetet är att ta fram en artefakt i form av en chatbot och utveckla dess dialog för en framtida implementation i en kundtjänst. Arbetet ämnar att ta fram designprinciper för utformning och utveckling av chatbotar och deras dialoger i en kundtjänstmiljö. Den forskningsmetod som tillämpades vid utvecklingen av artefakten var Design Science Research Methodology (DSRM). En litteraturstudie genomfördes och data samlades in genom möten samt en intervju med det företag som varit uppdragsgivare till arbetet. Arbetet resulterade i en demosida innehållande en chatbot, samt en sida för administratörer där de har en översikt av chatbotens genomförda interaktioner. Tre designprinciper togs även fram för utveckling av chatbotars dialog inom kundtjänst, vilka blev arbetets bidrag. De slutsatser som identifierades var att en chatbot bör kontrollera att användaren fått svar på sitt kundtjänstärende, en chatbot bör erbjuda mänsklig service vid missförstånd, en chatbot kan inte ersätta mänsklig service fullt ut samt att en chatbot bör ha en strukturerad datainsamling av genomförda interaktioner för att kunna utveckla och förbättra chatbotens dialog.
Automation of customer service through implementation of chatbots is becoming increasingly common in order to provide customers with a more accessible and efficient service. When implementing chatbots in customer services, human control and the customer experience are partially shifted to a digital system, which puts requirement on the chatbot’s dialogue. The purpose of this report is to develop an artifact for a client. The artifact is a web page containing a chatbot. The report aims to develop design principles for development of chatbots and their dialogues in a customer service. The research method used in the development of the artifact was Design Science Research Methodology (DSRM). A literature study was conducted, and data was collected through meetings and an interview with the client. The report resulted in a demo page containing a chatbot and a page for administrators with an overview of saved chats. Three design principles were also formulated for developing chatbots in customer service, which is the contribution of the report. The conclusions identified were that a chatbot should check that the user got the correct answer, a chatbot should offer human service in case of misunderstanding, a chatbot cannot fully replace human service and a chatbot should have a structured data collection of completed interactions for developing and improvement of the chatbot’s dialogue.

The implementation of chatbots and service services is becoming more common. The reason for this is that they are constantly available to answer questions, no matter what time it is. To make one chatbot is not just to write questions and specific answers. Communicating with one chatbot should, as much as possible, look like communicating with another human. The purpose of this report is to create a chatbot that will be used at Luleå university of technology and that will answer questions about system science. Furthermore, the goal is to investigate which design principles should be implemented, their possible concretization, when making chatbots, and possibly coming to new principles. The method used to make the chatbot is Design Science Research Methodology (DSRM). DSRM focuses on solving the problem by creating an IT artifact, which in this case is a chatbot. The result of this work is a created chatbot and design principles that were implemented during the development process.

Il natural language processing è un campo di ricerca interdisciplinare che spazia tra informatica, linguistica e intelligenza artificiale, che si pone come obiettivo il trattamento automatico del linguaggio naturale, ovvero l’analisi, la comprensione e l’elaborazione del linguaggio da parte dei calcolatori. Uno dei problemi più interessanti e ancora aperti di questa disciplina è la capacità di dialogo per la quale ricercatori e studiosi stanno ideando e impiegando nuovi approcci, in particolare basati su reti neurali artificiali, raggiungendo risultati sempre migliori. In questa tesi, oltre a dare una panoramica dello stato dell'arte, si espone lo sviluppo di un chatbot in contesto universitario, realizzato con il framework Rasa. Esso è pensato per gli studenti del Campus di Cesena e fornisce informazioni relative alla vita universitaria, principalmente sui corsi di laurea e sui bandi di Ateneo.

This paper researches how different amounts of data affect different word vector models for classification of dialog system user input. A hypothesis is tested that there is a data threshold for dense vector models to reach the state-of-the-art performance that have been shown with recent research, and that character-level n-gram word-vector classifiers are especially suited for Swedish classifiers–because of compounding and the character-level n-gram model ability to vectorize out-of-vocabulary words. Also, a second hypothesis is put forward that models trained with single statements are more suitable for chat user input classification than models trained with full conversations. The results are not able to support neither of our hypotheses but show that sparse vector models perform very well on the binary classification tasks used. Further, the results show that 799,544 words of data is insufficient for training dense vector models but that training the models with full conversations is sufficient for single statement classification as the single-statement- trained models do not show any improvement in classifying single statements.
Detta arbete undersöker hur olika datamängder påverkar olika slags ordvektormodeller för klassificering av indata till dialogsystem. Hypotesen att det finns ett tröskelvärde för träningsdatamängden där täta ordvektormodeller när den högsta moderna utvecklingsnivån samt att n-gram-ordvektor-klassificerare med bokstavs-noggrannhet lämpar sig särskilt väl för svenska klassificerare söks bevisas med stöd i att sammansättningar är särskilt produktiva i svenskan och att bokstavs-noggrannhet i modellerna gör att tidigare osedda ord kan klassificeras. Dessutom utvärderas hypotesen att klassificerare som tränas med enkla påståenden är bättre lämpade att klassificera indata i chattkonversationer än klassificerare som tränats med hela chattkonversationer. Resultaten stödjer ingendera hypotes utan visar istället att glesa vektormodeller presterar väldigt väl i de genomförda klassificeringstesterna. Utöver detta visar resultaten att datamängden 799 544 ord inte räcker till för att träna täta ordvektormodeller väl men att konversationer räcker gott och väl för att träna modeller för klassificering av frågor och påståenden i chattkonversationer, detta eftersom de modeller som tränats med användarindata, påstående för påstående, snarare än hela chattkonversationer, inte resulterar i bättre klassificerare för chattpåståenden.

Trots att antalet medier via vilka vi människor kan kommunicera med varandra är högre än någonsin, är talad interaktion något unikt betydelsefullt för våra mänskliga samhällen och relationer och därför ett ständigt relevant forskningsområde. Denna studie undersökte kvantitativa skillnader i hur människor konverserar med en talbaserad chattbot jämfört med en mänsklig konversationspartner, då de utförde en uppgift utformad för att skapa jämförliga dialoger. Resultatet visade på att konversationerna med chattbotten var mindre effektiva och ledde till sämre prestation i uppgiften. Dessutom påvisades att deltagarna använde en kortare genomsnittlig turlängd i konversationer med chattbotten, samt signifikanta skillnader i ordvariation mellan de två betingelserna. Dessa skillnader kan bero på att människor anpassar sitt språk efter sina uppfattningar av chattbottens kommunikativa egenskaper, och innebär att möjligheten att generalisera egenskaper hos människors tal i konversationer med liknande artificiella dialogpartners till konversationer med människor kan vara begränsad.

碩士
國立中央大學
資訊工程學系
107
In recent years, E-Learning has become more and more popular because of being able to let students learn anytime and anywhere. Compared with traditional classroom learning, students can adjust their learning more casually according to their own learning conditions. It can increase the efficiency of their learning. For a good e-learning platform, on-line tutor service is need. But hiring human tutors will cost a lot due to large number of students in whole time use. Therefore, we develop a chatbot system to share some of the work of human tutors: solve problems in the course for students and provide FAQ of the operation in the e-learning platform. It can even provide service to students via voice dialogue robots. With our system, students can get a more complete e-learning environment. The chatbot proposed in this paper is a retrieval-based model. After the user's input is segmented by the Hidden Markov Model to get the keywords, and the keywords are transmitted through the Word2vec model. The Word2Vec Model compares the similarity of the conversation topics defined in each database to achieve keyword extraction and classification for user conversations

碩士
朝陽科技大學
資訊工程系
106
Along with the advancement of technology and popularity, people’s communication way is influenced by Instant Messaging. The Chatbot technology is also rising. Most studies of Chatbot is focused on engineering aspect, that is: how to make better Chatbot. But the research on evaluation aspect is few. However, it is also important on how to evaluate the degree of different aspects in responses that replied by Chatbot. There are two major evaluation methods: automatic evaluation method and the evaluation method that judge by human. Although the automatic evaluation method can judge the dialogue system quickly, it has low correlation with human in many cases. On the other hand, judgement by human can avoid this situation. Therefore, the evaluation method can get more effective result at the evaluation method that judge by human. We will adopt the evaluation method that judge by human in our research. The evaluation rules in STC task of NTCIR are designed for general reply evaluation method. So it do not evaluate the expression degree in each aspects of responses. To design an evaluation method that can effective judge dialogue system is our research objective. By observing and analyze the evaluation methods of STC task in NTCIR, we designed a process of designing questionnaire, and find out factors with different aspects to design evaluation questions with different aspects for different question and answer types. We use consistency to judge our evaluation questions. In the experiments, we picked the dialog data with emotional expression type and analyzed it. In general, about the emotional expression type is venting his emotion. People might have different thoughts, and then the content of responses contains of sympathy, comfort and ridicule. So it needs to consider these different aspects in evaluation method. We designed the new evaluation questionnaire with different aspects, and verify it whether easily achieve consistency or not. In questionnaire survey result, we found out that the different aspects are easily achieve consistency. Therefore, our presented the process of design questionnaire that can make a new questionnaire to evaluate dialogues system with different aspects. In different corpus also suitable for our process of design questionnaire.

Para a comunicação entre seres humanos e computadores é necessária a identificação dos traços que os distinguem e das características do funcionamento de cada um. Desde a eletrónica, que é desenvolvida através de fenómenos físicos bem delineados, à informática, que assenta em axiomáticas matemáticas, o processo de funcionamento de um computador está livre de traços humanos e é conhecido por fornecer respostas concretas, verdadeiras e lógicas. Neste projeto foi desenvolvido um sistema de diálogo, denominado por PALbot com o objetivo de melhorar a acessibilidade na procura de informação para os utilizadores da plataforma do Ciberdúvidas. O PALbot é um programa que simula uma conversa humana, esclarecendo dúvidas relativamente à Língua Portuguesa, na forma de diálogo com o utilizador. Após desenvolvimento do chatbot, foi realizado um inquérito de forma a avaliar a ferramenta desenvolvida. Os resultados do inquérito revelam 65,54% de respostas corretas com a base de conhecimento da plataforma do Ciberdúvidas inserida no sistema de conversação. Adicionalmente, elaborou-se um conjunto de testes de forma a avaliar os atributos de qualidade, nomeadamente eficácia e eficiência, concluindo que 65,28% dos inquiridos concordam que o PALbot facilita quase sempre ou sempre o acesso à informação. Em suma, o chabot desenvolvido durante a presente dissertação apresenta potencial para melhorar a acessibilidade dos utilizadores na procura de informação bem como para auxiliar a plataforma Ciberdúvidas melhorando o esclarecimento de dúvidas relativas à Língua Portuguesa.
A good interaction between humans and computers is built on top of each other’s characteristics, functionality and behavior. From electronics, developed through actual physical phenomena, to informatics, built on mathematical axioms, the functionality of a computer is free of human trace. While computers are known for providing correct, true and logic answers, humans spend a vast amount of time on an informal dialog with almost no purpose. In this project, a dialog system named PALbot was developed to help Ciberdúvidas platform users access information. This program simulates a human conversation answering Portuguese linguistic questions to the user. After developing the chatbot, an inquire was made to evaluate the tool in question showing the program gave a correct answer 65.54% of times with the knowledge base of Ciberdúvidas platform. Additionally, another pool of tests was made to evaluate quality attributes such as efficiency and efficacy, in which was concluded that 65.28% of the enquired agree that PALbot always and almost always makes it easy to access to the information required. The chatbot developed during the current dissertation shows high potential to improve user’s accessibility to information as well as to help Ciberdúvidas platform answering Portuguese linguistic questions.

This diploma thesis deals with building a chatbot for the MojiLidi system, which helps to find specialists and companies providing their services and products. Chatbot is a type of interface that is controlled by a natural language conversation. Thus, users do not need to know the meaning of buttons or forms and for them it is enough just to say request. The work describes the main parts of chatbot such as understanding the natural language, managing the dialogue, creating responses, communication channel and the conversational user interface. Consequently, such a conversation agent is created and integrated into the MojiLidi web interface from where it helps users in 4 domains.

碩士
國立勤益科技大學
流通管理系
106
Due to the popularity and convenience of the Internet, the need to access the Internet anytime, anywhere is no longer a problem. What follows is what we need to do after we go online. The prevalence of APP has its roots in the ad lines that science and technology have always come from humanity. This is not just a line. As people’s needs become more and more diverse, a wide variety of APPs have also emerged under the design of people. But when we face so many assortment of APP software, In addition to busy comparing which is best, which one is the highest number of downloads, Often downloading later, it will find that it is not as convenient as we think it is or meet our needs. And the final fate of these downloaded apps is not hidden in one corner of our mobile phone, or is faced with being deleted. The birth of chat bots is not entirely to solve the dilemma of the above APP, but the action of chat dialogue is the most primitive and effective way of communication. Through the interaction of information exchange, in the process, clearly convey the needs and understanding and collect the useful information revealed in the dialogue, in addition to the traditional business model has been skillfully used in various business activities. Using technology to transfer the aforementioned techniques to the platform of chat bots, not only to make good use of the powerful capabilities of technology, but with increasingly sophisticated data, Internet of Things, etc., chat bots in the future The field of application, in addition to being broader, is bound to be closer to the people and collect more useful information to give back to the designer. This study compares the various types of chat robot software that have been developed so far and the most common problems encountered in physical distribution in the logistics industry. In traditional solutions, the most frequently occurring questions and answers are often FAQs. The function is only statically placed on the official website waiting for users to query. The technology such as chat robot should effectively improve the existing experience and bring more benefits and effects to the imagination space.

Dissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia
Atualmente a quantidade e facilidade de acesso a informação é estonteante. Em meros momentos, uma pessoa pode-se manter atualizada sobre quaisquer tópicos de interesse. Esta facilidade de acesso mudou a perspetiva das pessoas e agora não só é a qualidade de informação disponibilizada que é valorizada, como também a velocidade a que é fornecida.Além disso, hoje em dia as pessoas tem expectativas de que informação e serviços sejam fornecidos de uma maneira fácil e intuitiva. Uma maneira de responder às expectativas das pessoas é através de assistentes virtuais. Os chatbots fornecem informação em tempo real e as interações com eles são feitas de uma forma fácil e intuitiva -- através de linguagem natural.Com a evolução das necessidades das empresas e das pessoas, a Critical Software (CSW) optou apoiar a criação de uma plataforma -- Lexia -- para o desenvolvimento de assistentes virtuais que possam interagir em vários domínios/contextos diferentes (por exemplo: podem agir como assistentes num banco ou como assistente para reservar quartos de hotel).Esta dissertação apresenta a primeira versão do Lexia. Esta primeira versão é capaz de dialogar com utilizadores e de ser implementada em vários contextos (e de executar tarefas dentro desses contextos). Usando a CSW como um caso de estudo, um agente conversacional que consegue interagir com sistemas internos desta empresa foi implementado.A versão do Lexia desenvolvida serve de fundação para possível trabalho futuro ser desenvolvido. Uma das maneiras possíveis de construir sobre esta versão é adicionando capacidades cognitivas ao sistema.
We live days in which the quantity of and rapid access to information available is staggering. In moments, a person may keep him or herself updated on topics of interest. This ease of access to information has changed people's perspectives and now, not only is the quality of information provided valued, but also the speed at which it is provided.Adding to the previous point, nowadays people expect information and services to be provided in a easy and intuitive way. A way to address the aforementioned problems is through the use of virtual assistants. Virtual assistants provide information in real-time and are interacted in a simple, intuitive way -- through natural language.With the evolution of people's and companies' needs, Critical Software (CSW) decided to go forward with the creation of a platform -- Lexia -- for developing virtual assistants that can be deployed (and execute tasks) in various different contexts/domains (e.g. deployed as an assistant in a bank or as an assistant to book hotels). This dissertation presents the first version of Lexia. This first version is capable of dialoguing with users and be deployed within various contexts (and execute tasks within those domains). Using CSW as a case study, a conversation engine that can interact with CSW's internal systems was deployed.The Lexia version developed in this internship lays the groundwork for future work to be developed. A possible way to build upon this version is to add cognitive capabilities to the platform.

This project described in this dissertation is being carried out for the Ministry of Social and Economic Inclusion (MIES) of Ecuador based on its current problems. The de ciencies that government entities have to help their citizens with information and paperwork has exceeded their operational capacity. The MIES currently has a Marketing and Information department that is saturated with questions through channels such as call centers, information centers in their of- ces and social networks outside their o ce hours. In recent years there has been an increase in requests for information through digital channels such as its Facebook page, since internet access to places far from the big cities has increased. This has been seen as an opportunity for improvement by creating an chatbot agent that helps citizens 24 hours a day, 7 days a week. Most of the queries can be made through a query to their internal data and this allows the operational burden of the operators to be released to carry out management processes and not just information. Many public and private companies have resorted to using chatbots to help their users with simple information tasks. They have also relied on these technological tools to create registration and management functions. Today we can use chatbots development tools and platforms such as Dialog ow that allow to create chatbots in a manageable and scalable way according to needs. Facebook has multiple connection tools that allow it to integrate safely and e ciently with its platforms such as Facebook Messenger, allowing customers to create applications that will reach the majority of citizens who have internet access. Developing a chatbot agent can be a simple and straightforward task, but in which the remaining time must be invested in training and helping the chatbot agent to understand words or idioms of language used in di erent regions of the same country. In the development of a chatbot, the training cycle is constant and allows the chatbot to increase its ability to understand the users who use them. In the tests carried out on this chatbot, it was concluded that although the use of these tools allows to release the operational load, it does not avoid the need for users to interact with natural persons, but the requirement is drastically reduced. In the tests it was also obtained that many problems can be obtained by nding a wide range of synonyms and local expressions, but correct training and constant review of the answers provided helps the chatbot to self-train and evolve its answers over time interactions.

Com a evolução da tecnologia e consequente proliferação da utilização da internet tendo como finalidade, realizar compras online, e aliado à forte globalização do comércio global, que tem o comércio online como expoente máximo, é cada vez mais difícil às empresas ganhar uma vantagem competitiva em relação aos seus concorrentes, tornandose assim fundamental colocar a satisfação dos consumidores no centro dos seus negócios. Esta investigação pretende analisar a forma como a utilização de interfaces de linguagem natural, juntamente com um sistema de recomendação inteligente, isto é, a aposta no conceito desenvolvido por Chris Messina (2015), Conversational Commerce, poderá ser um fator diferenciador no relacionamento das empresas com os seus consumidores, permitindo não só ganhar uma vantagem competitiva, mas também potencializar a sua marca no mercado onde atua. Esta investigação e os seus resultados permitem demonstrar que a utilização destas interfaces conversacionais, apoiados em linguagem natural, permitem aumentar a confiança e satisfação dos consumidores, tornando o processo de compra mais fluido, flexível, conveniente e rápido, ganhando desta forma uma vantagem competitiva sobre os seus concorrentes
With the evolution of technology and the consequent proliferation of the use of the internet for online shopping, and allied to the strong globalization of global commerce, which has online commerce as the highest exponent, it is increasingly difficult for companies to gain a competitive advantage over its competitors, making it fundamental to place consumer satisfaction at the heart of its business. This research intends to analyse how the use of natural language interfaces, together with a system of intelligent recommendation, that is to say, the concept developed by Chris Messina (2015), Conversational Commerce, could be a differentiating factor in the relationship of companies with its consumers, allowing not only to gain a competitive advantage, but to influence company reputation improving the brand image. This research and its results demonstrate that the use of these conversational interfaces, supported by natural language, increases trust and consumer satisfaction, making the purchasing process more fluid, flexible, convenient and fast, thus gaining a market advantage over its competitors.