Bibliographies thématiques / Syntactic feature

Sommaire

  1. Articles de revues
  2. Thèses
  3. Livres
  4. Chapitres de livres
  5. Actes de conférences

Littérature scientifique sur le sujet « Syntactic feature »

Auteur : Grafiati
Publié le 9 mars 2023
Mis à jour le 10 mars 2023

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres

Choisissez une source :

Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Syntactic feature ».

À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.

Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.

Articles de revues sur le sujet "Syntactic feature"

1

Zhang, Xiaohan, Shaonan Wang, Nan Lin, Jiajun Zhang et Chengqing Zong. « Probing Word Syntactic Representations in the Brain by a Feature Elimination Method ». Proceedings of the AAAI Conference on Artificial Intelligence 36, no 10 (28 juin 2022) : 11721–29. http://dx.doi.org/10.1609/aaai.v36i10.21427.

Texte intégral
Résumé :
Neuroimaging studies have identified multiple brain regions that are associated with semantic and syntactic processing when comprehending language. However, existing methods cannot explore the neural correlates of fine-grained word syntactic features, such as part-of-speech and dependency relations. This paper proposes an alternative framework to study how different word syntactic features are represented in the brain. To separate each syntactic feature, we propose a feature elimination method, called Mean Vector Null space Projection (MVNP). This method can remove a specific feature from word representations, resulting in one-feature-removed representations. Then we respectively associate one-feature-removed and the original word vectors with brain imaging data to explore how the brain represents the removed feature. This paper for the first time studies the cortical representations of multiple fine-grained syntactic features simultaneously and suggests some possible contributions of several brain regions to the complex division of syntactic processing. These findings indicate that the brain foundations of syntactic information processing might be broader than those suggested by classical studies.
Styles APA, Harvard, Vancouver, ISO, etc.
2

BJÖRKLUND, JOHANNA, et NIKLAS ZECHNER. « Syntactic methods for topic-independent authorship attribution ». Natural Language Engineering 23, no 5 (9 août 2017) : 789–806. http://dx.doi.org/10.1017/s1351324917000249.

Texte intégral
Résumé :
AbstractThe efficacy of syntactic features for topic-independent authorship attribution is evaluated, taking a feature set of frequencies of words and punctuation marks as baseline. The features are ‘deep’ in the sense that they are derived by parsing the subject texts, in contrast to ‘shallow’ syntactic features for which a part-of-speech analysis is enough. The experiments are made on two corpora of online texts and one corpus of novels written around the year 1900. The classification tasks include classical closed-world authorship attribution, identification of separate texts among the works of one author, and cross-topic authorship attribution. In the first tasks, the feature sets were fairly evenly matched, but for the last task, the syntax-based feature set outperformed the baseline feature set. These results suggest that, compared to lexical features, syntactic features are more robust to changes in topic.
Styles APA, Harvard, Vancouver, ISO, etc.
3

Al Zahrani, Mohammad Ali. « The Multifunctionality of a Morpheme Proposes its Morphosyntactic Features and their Specifications : Feature Matrix ». Vivid : Journal of Language and Literature 9, no 2 (9 décembre 2020) : 66. http://dx.doi.org/10.25077/vj.9.2.66-79.2020.

Texte intégral
Résumé :
Multifunctionality is a cross linguistic phenomenon. It refers to the linguistic capability of a linguistic form to manifest itself in different syntactic structures that result in different syntactic functions. Treating multifunctionality from a generative perspective, the paper focuses on the different functions of the Hijazi Arabic (HA) maa and contributes to the HA literature by describing these different functions and claiming that they are not instances of homonymy, but of multifunctionality. Those different functions are governed by the different syntactic environments that maa occurs in. Its occurrence in multiple syntactic environments suggests that maa has a feature matrix that includes its morphosyntactic features and their specifications that express the appropriate use and interpretation of a given structure. The findings show that maa may function as a negative particle, emphatic particle, relative pronoun, infinitival particle, conditional particle, interrogative particle, exclamative particle and a particle of inclusion. These uses differ in their syntactic flexibility and rigidity (restrictedness). Although more than one function can incorporate to express multiple senses, the salient point about the different functions of maa is that there is no semantic or syntactic ambiguity between its functions.
Styles APA, Harvard, Vancouver, ISO, etc.
4

Al Zahrani, Mohammad Ali. « The Multifunctionality of a Morpheme Proposes its Morphosyntactic Features and their Specifications : Feature Matrix ». Vivid : Journal of Language and Literature 9, no 2 (9 décembre 2020) : 66. http://dx.doi.org/10.25077/vj.9.2.66-79.2020.

Texte intégral
Résumé :
Multifunctionality is a cross linguistic phenomenon. It refers to the linguistic capability of a linguistic form to manifest itself in different syntactic structures that result in different syntactic functions. Treating multifunctionality from a generative perspective, the paper focuses on the different functions of the Hijazi Arabic (HA) maa and contributes to the HA literature by describing these different functions and claiming that they are not instances of homonymy, but of multifunctionality. Those different functions are governed by the different syntactic environments that maa occurs in. Its occurrence in multiple syntactic environments suggests that maa has a feature matrix that includes its morphosyntactic features and their specifications that express the appropriate use and interpretation of a given structure. The findings show that maa may function as a negative particle, emphatic particle, relative pronoun, infinitival particle, conditional particle, interrogative particle, exclamative particle and a particle of inclusion. These uses differ in their syntactic flexibility and rigidity (restrictedness). Although more than one function can incorporate to express multiple senses, the salient point about the different functions of maa is that there is no semantic or syntactic ambiguity between its functions.
Styles APA, Harvard, Vancouver, ISO, etc.
5

Wen, Yan, Wenkai Li, Qingtian Zeng, Hua Duan, Feng Zhang et Shitao Kang. « Syntactic Knowledge Embedding Network for Aspect-Based Sentiment Classification ». Mobile Information Systems 2022 (15 avril 2022) : 1–8. http://dx.doi.org/10.1155/2022/1352028.

Texte intégral
Résumé :
An aspect-based sentiment classification task is a fine-grained sentiment analysis task, which is aimed at identifying the sentiment polarity of a given aspect in subjective sentences. In recent years, some researchers have applied pretrained BERT models to this task. However, existing research only uses the BERT output layer and ignores the syntactic features in the middle layers, leading to deviations in the prediction results. In order to solve above problems, we propose a new model BERT-SFE. Firstly, we explicitly utilize the middle layers of BERT to capture the underlying syntactic features. Secondly, we construct a syntactic feature extraction unit based on Star-Transformer, which uses an auxiliary vector and the star network structure to capture both local and global syntactic information in a sentence. Finally, we merge the syntactic features with the semantic features from the BERT output layer in the feature fusion layer, obtaining a more accurate sentiment representation of the aspect. The experimental results on three public ABSA datasets show that using the syntactic feature extraction unit based on Star-Transformer to mine the syntactic knowledge in the middle layers of BERT can effectively improve the accuracy of sentiment classification. BERT-SFE achieves the best performance compared with existing models.
Styles APA, Harvard, Vancouver, ISO, etc.
6

Pullum, Geoffrey K., et Arnold M. Zwicky. « Phonological Resolution of Syntactic Feature Conflict ». Language 62, no 4 (décembre 1986) : 751. http://dx.doi.org/10.2307/415171.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Kučerová, Ivona, et Adam Szczegielniak. « Roots, their structure and consequences for derivational timing ». Linguistic Review 36, no 3 (25 septembre 2019) : 365–87. http://dx.doi.org/10.1515/tlr-2019-2022.

Texte intégral
Résumé :
Abstract Recent work in Distributed Morphology, most prominently Harley (2014), argues for roots being able to take syntactic complements, which opens the door for the possibility of having syntactic features within a root’s representation – something most DM literature rejects (Embick 2015). Upon a closer inspection of the arguments presented in the literature, it is not clear whether the disagreement has an empirical underpinning, or whether it stems from the lack of methodological clarity as far as the identification of the precise nature of what constitutes a syntactic feature. This paper takes this methodological question seriously and investigates a type of derivational behavior that, in our view, provides a decisive argument for the presence of syntactic features on roots. We argue that the presence of a syntactic feature on the root can be conclusively established based on a feature’s impact on specific properties within a larger syntactic structure. Based on empirical evidence form gender agreement phenomena, we introduce a model of grammar that distinguishes roots with syntactic features from those which do not have them. We propose that such a distinction between roots will manifest itself in the timing of root insertion – roots without syntactic features are late inserted, while roots with syntactic features must be early inserted.
Styles APA, Harvard, Vancouver, ISO, etc.
8

Sigurðsson, Halldór Ármann. « Universality and variation in language ». Lexical Issues in the Architecture of the Language Faculty 2, no 1 (6 novembre 2020) : 5–29. http://dx.doi.org/10.1075/elt.00013.sir.

Texte intégral
Résumé :
Abstract This article discusses language universality and language variation, and suggests that there is no feature variation in initial syntax, featural variation arising by metamorphosis under transfer from syntax to PF-morphology. In particular, it explores the Zero Hypothesis, stating that Universal Grammar, UG, only provides two building elements, Root Zero and Edge Feature Zero, zero, as they are purely structural/formal elements with no semantic content in UG. Their potential content is provided by the Concept Mine, a mind-internal but language-external department. UG and narrow syntax has access to the Concept Mine, and this Syntax-Concept Access is unique to humans, a prerequisite for the evolution of language (Section 1). A related idea (also in Section 1) is coined the Generalized Edge Feature Approach, GEFA. It states that Merge always involves at least one edge feature, which precludes symmetric structures and enables Simplest Merge (no Pair-Merge, no Hilbert epsilon operator). The article advocates that there is no syntactic feature selection (Section 2), all syntactic features being universally accessible in the Concept Mine, via Root Zero and Edge Feature Zero. In contrast, there is feature selection in PF (including morphology), yielding variation (Section 3), Gender being a clear example (Section 4). However, there is a widely neglected syntax-to-PF-morphology metamorphosis (Section 5), such that morphological features like [past] are distinct from albeit related to syntactic features like Speech Time. Parameters operate on selected PF features, and not on purely syntactic features, so parameter setting is plausibly closely tied to the syntax-to-PF-morphology metamorphosis (the concluding Section 6). It is suggested that parameters are on the externalization side of language, part of or related to the sensory-motor system, facilitating motoric learning in language acquisition.
Styles APA, Harvard, Vancouver, ISO, etc.
9

Copstein, Rafael, Egil Karlsen, Jeff Schwartzentruber, Nur Zincir-Heywood et Malcolm Heywood. « Exploring syntactical features for anomaly detection in application logs ». it - Information Technology 64, no 1-2 (23 mars 2022) : 15–27. http://dx.doi.org/10.1515/itit-2021-0064.

Texte intégral
Résumé :
Abstract In this research, we analyze the effect of lightweight syntactical feature extraction techniques from the field of information retrieval for log abstraction in information security. To this end, we evaluate three feature extraction techniques and three clustering algorithms on four different security datasets for anomaly detection. Results demonstrate that these techniques have a role to play for log abstraction in the form of extracting syntactic features which improves the identification of anomalous minority classes, specifically in homogeneous security datasets.
Styles APA, Harvard, Vancouver, ISO, etc.
10

Zeijlstra, Hedde. « How semantics dictates the syntactic vocabulary ». ZAS Papers in Linguistics 44, no 2 (1 janvier 2006) : 437–51. http://dx.doi.org/10.21248/zaspil.44.2006.328.

Texte intégral
Résumé :
In this paper I argue that the set of formal features that can head a functional projection is not given by UG but derived through L1 acquisition. I formulate a hypothesis that says that initially every functional category F is realised as a semantic feature [F]; whenever there is an overt doubling effect in the L1 input with respect to F, this semantic feature [F] is reanalysed as a formal feature [i/uF]. In the first part of the paper I provide a theoretical motivation for this hypothesis, in the second part I test this proposal for a case-study, namely the cross-linguistic distribution of Negative Concord (NC). I demonstrate that in NC languages negation has been reanalysed as a formal feature [i/uNEG], whereas in Double Negation languages this feature remains a semantic feature [NEG] (always interpreted as a negative operator), thus paving the way for an explanation of NC in terms of syntactic agreement. In the third part I discuss that the application of the hypothesis to the phenomenon of negation yields two predictions that can be tested empirically. First I demonstrate that negative markers X° can be available only in NC languages; second, independent change of the syntactic status of negative markers, can invoke a change with respect to the exhibition of NC in a particular language. Both predictions are proven to be correct. I finally argue what the consequences of the proposal presented in this paper are for both the syntactic structure of the clause and second for the way parameters are associated to lexical items.
Styles APA, Harvard, Vancouver, ISO, etc.
Plus de sources

Thèses sur le sujet "Syntactic feature"

1

Anderson, Michael Don. « Ellipsis as a Diagnostic Tool of Feature Strength and the Syntactic Structure of Ilocano ». Diss., The University of Arizona, 2009. http://hdl.handle.net/10150/195692.

Texte intégral
Résumé :
This dissertation examines Ilocano, an Austronesian Filipino language, within the Minimalist Framework, in an effort to tease apart the general syntactic properties of the language. I show that Ilocano underlying structure can easily be captured within the standard syntactic structures proposed for languages generally (Universal Grammar). In my examination of ellipsis in Ilocano, I concern myself strictly with syntactic and not semantic properties. I show that syntactic feature distribution (e.g. [+FOC], [+NEG], [+DET]) in combination with the two basic operations of the Minimalist Program: FEATURE-CHECKING and MERGE can account for both the underlying structure of Ilocano utterances as well as the word-order at Spell-Out, without making any stipulations not found in languages generally.My research also reveals new insights and corrects existing assumptions about certain previously undiscovered underlying structural properties of Ilocano. I account for the restrictive word ordering and structure found in Ilocano by assigning a universally applicable, non-controversial set of functional and lexical features to morphemes. These features satisfy, individually or collectively, feature-checking requirements in the language, resulting in the attested output of Ilocano. The types of ellipsis considered as a diagnostic toward that end are: NP-ellipsis, Bare Argument Ellipsis/Stripping, Gapping, Sluicing and Psuedogapping. I argue that the primary mechanism which licenses ellipsis in Ilocano is FOCUS-RAISING which allows extraction of remnant material prior to ellipsis of the TP in the case of all verbal-type ellipsis in Ilocano; or the DP in terms of Ilocano NP-ellipsis.
Styles APA, Harvard, Vancouver, ISO, etc.
2

Ssempuuma, Jude [Herausgeber]. « Morphological and Syntactic Feature Analysis of Ugandan English : Influence from Luganda, Runyankole-Rukiga, and Acholi-Lango ». Frankfurt a.M. : Peter Lang GmbH, Internationaler Verlag der Wissenschaften, 2018. http://d-nb.info/118148801X/34.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

GENOVESE, GIULIANA. « L'infant-directed speech nella lingua italiana : caratteristiche lessicali, sintattiche, prosodiche e relazione con lo sviluppo linguistico ». Doctoral thesis, Università degli Studi di Milano-Bicocca, 2019. http://hdl.handle.net/10281/241109.

Texte intégral
Résumé :
Il presente lavoro di ricerca intende indagare le caratteristiche del linguaggio rivolto ai bambini nella lingua italiana nel primo anno di vita e i suoi effetti sullo sviluppo del linguaggio, dai prerequisiti allo sviluppo lessicale e sintattico. La cornice teorica su cui si fondano le ricerche qui presentate assume che il processo di acquisizione linguistica abbia basi sociali. La prima parte dell’elaborato comprende due studi che descrivono le proprietà lessicali, sintattiche e prosodiche del linguaggio rivolto ai bambini. La seconda, invece, è costituita da due lavori che indagano la qualità e gli effetti dell’input linguistico nello sviluppo del linguaggio, prendendo in considerazione sia un prerequisito in fase verbale, sia le competenze lessicali e sintattiche nel secondo anno di vita; in questa seconda parte sono stati inoltre definiti i predittori dell’apprendimento linguistico, considerando sia le caratteristiche dell’input ma anche il contributo delle competenze comunicative precoci del bambino. Il primo studio presentato è un’indagine a carattere longitudinale nella quale sono state descritte, mediante misure globali e specifiche, le caratteristiche lessicali e sintattiche del linguaggio rivolto ai bambini nella lingua italiana. Ciò che è emerso è un registro semplificato ma non semplice che presenta un periodo di massima semplificazione nella seconda metà del primo anno di vita. La seconda ricerca, sempre a carattere longitudinale, ha preso in esame le proprietà prosodiche del linguaggio rivolto ai bambini e la caratterizzazione prosodica di enunciati con funzione pragmatica differente. I risultati hanno messo in luce una prosodia generalmente enfatizzata nel linguaggio rivolgo ai bambini nel periodo preverbale ma, sorprendentemente, in misura moderata. Inoltre, è stato possibile osservare un pattern di cambiamento nel corso del primo anno di vita che si discosta da quello caratterizzante altre lingue non-tonali. Infine, sono emerse caratteristiche prosodiche distintive per enunciati con funzione pragmatica diversa, elemento che evidenzia il ruolo altamente informativo della prosodia. Il terzo lavoro ha indagato longitudinalmente gli antecedenti dello sviluppo linguistico, valutando il contributo delle competenze comunicative precoci del bambino e il ruolo dell’input - di cui sono state esaminate qualità e stabilità - temi rispetto ai quali la letteratura riporta ancora risultati contrastanti. I dati ottenuti indicano che lo sviluppo linguistico nel secondo anno di vita rispecchi le abilità comunicative precoci e sembri favorito da un input ricco, ridondante e sintatticamente articolato. Infine, il quarto contributo ha analizzato, con un disegno sperimentale, i possibili effetti del canto rivolto ai bambini, ipotizzando un ruolo facilitatore rispetto al parlato nel processo di discriminazione fonetica, precursore preverbale dello sviluppo linguistico. Si tratta di un tema piuttosto trascurato nella letteratura che, invece, si è di fatto sempre concentrata sugli effetti della prosodia tipica del parlato rivolto ai bambini. I risultati principali hanno messo in luce come il ruolo facilitatore del canto in tale registro emerga alla fine del primo anno di vita quando, da un punto di vista evolutivo, si verifica un cambiamento nella capacità di discriminare i fonemi nativi e non nativi. È stato altresì possibile individuare benefici di una maggiore esposizione alla musica e al canto in fase preverbale, sia rispetto alla discriminazione fonetica che al successivo sviluppo lessicale.
This research work aims to explore infant-directed speech features in Italian language during the first year of an infant’s life and its effects on language acquisition, from precursors to advanced lexical and syntactic skills. The theoretical background assumes social bases of linguistic development. The first part consists of two studies on lexical, syntactic and prosodic properties in this special register. The second part includes two researches on quality and effects of linguistic input in language acquisition, taking into account a preverbal precursor and lexical and syntactic abilities during the second year of life; additionally, in this section, the predictors of language learning have been defined, exploring the role of linguistic input and the contribution of early communication skills in infants. The first study is a longitudinal design investigation, with an exhaustive analysis of lexical and syntactic characteristics of infant-directed speech in Italian language, comprehensive of both global and specific measures. From this investigation, the special register addressed to infants appears as a simplified but not simple with a period of maximum simplification in the second half of the first year of an infant’s life. The second longitudinal research examines prosodic properties in infant-directed speech and prosodic characterization of utterances with different pragmatic function. Results show how typical prosody in Italian infant-directed speech is overall emphasized in the preverbal period but, surprisingly, moderately; moreover, prosody changes during the first year even though without the same pattern of other non-tonal languages. Lastly, utterances with different pragmatic functions are characterized by a distinctive prosody. In the third contribution, predictors of language acquisition are longitudinally explored, analyzing the role of early communication skills in infants and of maternal input. In addition, input quality and stability are evaluated. About this topic, literature shows conflicting results. Overall, we find how subsequent linguistic abilities could be predicted by infant’s early communication skills and a by a rich, redundant, syntactically articulated but lexically repetitive input. Lastly, the fourth experimental work analyses the facilitator role of infant-directed song compared to infant-directed speech on the phonetic discrimination process, a preverbal precursor of language acquisition. Literature highlights how typical prosody in this special speech supports the identification of linguistic units in the verbal flow. Nevertheless, the role of infant-directed song has been poorly explored, especially as regard the development of a linguistic prerequisite. Main results prove a facilitator role of infant-directed song at the end of the first year of an infant’s life, when changes in the phonetic discrimination skill occur. Moreover, we find benefic effects of an higher musical and song exposition during the preverbal stage on both phonetic discrimination and subsequent lexical skills.
Styles APA, Harvard, Vancouver, ISO, etc.
4

Ssempuuma, Jude [Verfasser], Christiane [Gutachter] Meierkord et Ulrike [Gutachter] Gut. « Morphological and syntactic feature analysis of Ugandan english : influence from Luganda, Runyankole-Rukiga, and Acholi-Lango / Jude Ssempuuma ; Gutachter : Christiane Meierkord, Ulrike Gut ; Fakultät für Philologie ». Bochum : Ruhr-Universität Bochum, 2019. http://d-nb.info/1182682553/34.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
5

Brigadoi, Ivan. « Genre classification using syntactic features ». Thesis, Uppsala universitet, Institutionen för lingvistik och filologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-454667.

Texte intégral
Résumé :
This thesis work adresses text classification in relation to genre identification using different feature sets, with a focus on syntactic based features. We built our models by means of traditional machine learning algorithms, i.e. Naive Bayes, K-nearest neighbour, Support Vector Machine and Random Forest in order to predict the literary genre of books. We trained our models using as feature sets bag-of-words (BOW), bigrams, syntactic-based bigrams and emotional features, as well as combinations of features. Results obtained using the best features, i.e. BOW combined with bigrams based on syntactic relations between words, on the test set showed an enhancement in performance by 2% in F1-score over the baseline using BOW features, which translates into a positive impact of using syntactic information in the task of text classification.
Styles APA, Harvard, Vancouver, ISO, etc.
6

Lumsden, John Stewart. « Syntactic features : parametric variation in the history of English ». Thesis, Massachusetts Institute of Technology, 1987. http://hdl.handle.net/1721.1/14702.

Texte intégral
Résumé :
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Linguistics and Philosophy, 1987.
Title as it appears in M.I.T. Graduate List, Sept. 1987: Syntactic features--parameters in the history of English.
Bibliography: v. 2, leaves 418-422.
by John Stewart Lumsden.
Ph.D.
Styles APA, Harvard, Vancouver, ISO, etc.
7

Nădejde, Maria. « Syntactic and semantic features for statistical and neural machine translation ». Thesis, University of Edinburgh, 2018. http://hdl.handle.net/1842/31346.

Texte intégral
Résumé :
Machine Translation (MT) for language pairs with long distance dependencies and word reordering, such as German-English, is prone to producing output that is lexically or syntactically incoherent. Statistical MT (SMT) models used explicit or latent syntax to improve reordering, however failed at capturing other long distance dependencies. This thesis explores how explicit sentence-level syntactic information can improve translation for such complex linguistic phenomena. In particular, we work at the level of the syntactic-semantic interface with representations conveying the predicate-argument structures. These are essential to preserving semantics in translation and SMT systems have long struggled to model them. String-to-tree SMT systems use explicit target syntax to handle long-distance reordering, but make strong independence assumptions which lead to inconsistent lexical choices. To address this, we propose a Selectional Preferences feature which models the semantic affinities between target predicates and their argument fillers using the target dependency relations available in the decoder. We found that our feature is not effective in a string-to-tree system for German-English and that often the conditioning context is wrong because of mistranslated verbs. To improve verb translation, we proposed a Neural Verb Lexicon Model (NVLM) incorporating sentence-level syntactic context from the source which carries relevant semantic information for verb disambiguation. When used as an extra feature for re-ranking the output of a German-English string-to-tree system, the NVLM improved verb translation precision by up to 2.7% and recall by up to 7.4%. While the NVLM improved some aspects of translation, other syntactic and lexical inconsistencies are not being addressed by a linear combination of independent models. In contrast to SMT, neural machine translation (NMT) avoids strong independence assumptions thus generating more fluent translations and capturing some long-distance dependencies. Still, incorporating additional linguistic information can improve translation quality. We proposed a method for tightly coupling target words and syntax in the NMT decoder. To represent syntax explicitly, we used CCG supertags, which encode subcategorization information, capturing long distance dependencies and attachments. Our method improved translation quality on several difficult linguistic constructs, including prepositional phrases which are the most frequent type of predicate arguments. These improvements over a strong baseline NMT system were consistent across two language pairs: 0.9 BLEU for German-English and 1.2 BLEU for Romanian-English.
Styles APA, Harvard, Vancouver, ISO, etc.
8

Holmberg, Anders. « Word order and syntactic features in the Scandinavian languages and English / ». Stockholm : Dept. of General Linguistics, University of Stockholm, 1986. http://bibpurl.oclc.org/web/33078.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

Sundström, Alex. « Investigation into predicting unit test failure using syntactic source code features ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233382.

Texte intégral
Résumé :
In this thesis the application of software defect prediction to predict unit test failure is investigated. Data for this purpose was collected from a Continuous Integration development environment. Experiments were performed using semantic features from the source code. As the data was imbalanced with defective samples being in minority different degrees of oversampling were also evaluated. The data collection process revealed that even though several different code commits were available few ever failed a unit test. Difficulties with linking a failure to a specific file were also encountered. The machine learning model used in the project produced poor results when compared against related work, from which it was based on. In F-measure, it on average achieve 53% of the mean performance of state-of-the-art for software defect prediction on bugs in Java source files. Specifically, it would appear that very little information was available for the model to learn defects in files not present in training data.
I denna avhandling undersöks applikationen av prognos för mjukvarudefekter för att förutse enhetstestfel. Data för detta syfte samlades in från en utvecklingsmiljö med kontinuerlig integration. Experimenten utfördes med användning av semantiska särdrag samlade från källkod. Då data var obalanserat med defekta exempel i minoritet evaluerades olika grader av översampling. Datainsamlingsprocessen visade att även om det fanns många kodinlämningar så misslyckades få någonsin ett enhetstest. Svårigheter med att länka testmisslyckanden till en specifik fil påträffades också. Den använda maskininlärningsmodellen uppvisade också dåliga resultat i jämförelse med relaterade värk. Mätt i F-measure uppnåddes i genomsnitt 53% av genomsnittlig prestandan av bästa möjliga prognos av mjukvarudefekter av buggar i Java källkod. Specifikt så framträdde det att väldigt lite information verkar finnas för modellen att lära sig defekter i filer som ej fanns med i träningsdata.
Styles APA, Harvard, Vancouver, ISO, etc.
10

Cook, Angela Elizabeth. « A Linguistic Analysis of Selected Morpho-syntactic Features of Spoken Mandarin ». Thesis, Griffith University, 2014. http://hdl.handle.net/10072/367028.

Texte intégral
Résumé :
This dissertation carries out a linguistic analysis of three selected morpho-syntactic features of Modern Standard Chinese using a corpus of spoken data. It aims to contribute to a better understanding of Mandarin Chinese grammar by making two quite different contributions to the body of research. Firstly, it provides a reconceptualised analysis of the existing literature on morpho-syntactic language change in Modern Standard Chinese, which is presented both diagrammatically and in textual form. The reconceptualisation of previous findings reveals some important and interesting correlations and connections that were not immediately obvious from the existing literature, owing to the disparate and ad hoc nature in which they have often been presented. It is hoped that a flow-on effect of this unified classification schema will be to encourage a more systematic, organised and manageable approach to conducting and reporting on future research into Chinese morpho-syntactic language change. The second contribution is a detailed grammatical analysis of selected morpho-syntactic features of Mandarin Chinese, which is carried out using a corpus of spoken data assembled especially for the purposes of this research. The corpus consists of transcripts of the chat show ‘A Date with Luyu’ broadcast between January and September 2011, and totals over 500,000 characters in size.
Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
School of Languages and Linguistics
Arts, Education and Law
Full Text
Styles APA, Harvard, Vancouver, ISO, etc.
Plus de sources

Livres sur le sujet "Syntactic feature"

1

Tomić, Olga Mišeska. Balkan Sprachbund Morpho-Syntactic Features. Dordrecht : Springer Netherlands, 2006. http://dx.doi.org/10.1007/1-4020-4488-7.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
2

Brill, Frances. Analysing syntactic and textual linguistic features in relation to text-type and mode. Manchester : University of Manchester, 1995.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

Volpato, Francesca. Relative Clauses, Phi Features, and Memory Skills. Venice : Edizioni Ca' Foscari, 2019. http://dx.doi.org/10.30687/978-88-6969-392-2.

Texte intégral
Résumé :
This volume deals with the syntactic competence of Italian-speaking individuals with hearing impairment (cochlear implant users and LIS signers) and individuals with normal hearing (children, adolescents, and adults), focusing on relative clauses, a central topic in current research. The volume also presents the participants’ performance in different memory tasks discussing the relationship between sentence comprehension and memory resources in children with hearing impairment and with normal hearing.
Styles APA, Harvard, Vancouver, ISO, etc.
4

Marcato, Enrico. Personal Names in the Aramaic Inscriptions of Hatra. Venice : Edizioni Ca' Foscari, 2018. http://dx.doi.org/10.30687/978-88-6969-231-4.

Texte intégral
Résumé :
This book offers a comprehensive linguistic evaluation of the 376 personal names attested in the roughly 600 Aramaic inscriptions of Hatra, the famous Northern Mesopotamian city that flourished in the Parthian age, between the 1st century BC and the 3rd century AD. This study benefits from the publication of many Hatran inscriptions during recent decades, which have yielded rich onomastic data, and some fresh readings of these epigraphic sources. This work is subdivided into three main parts: an “Onomastic Catalogue”, a “Linguistic Analysis”, and a “Concordances Section”. The “Catalogue” is organized as a list of entries, in which every name is transliterated, translated (whenever possible), discussed from an etymological perspective, provided with onomastic parallels, and accompanied by its attestations in the Hatran Aramaic corpus. The “Catalogue” is followed by a “Linguistic Analysis” which describes, firstly, the principal orthographic, phonological, morphological, and syntactical features of Hatran names. The linguistic discussion proper is followed by a semantic taxonomy of the names which make up the corpus and an overview of the religious significance of the theophoric names. “Charts of Concordances” end the book.
Styles APA, Harvard, Vancouver, ISO, etc.
5

Boeckx, Cedric. Elementary Syntactic Structures : Prospects of a Feature-Free Syntax. Cambridge University Press, 2014.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Boeckx, Cedric. Elementary Syntactic Structures : Prospects of a Feature-Free Syntax. Cambridge University Press, 2014.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Boeckx, Cedric. Elementary Syntactic Structures : Prospects of a Feature-Free Syntax. Cambridge University Press, 2014.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
8

Elementary Syntactic Structures : Prospects of a Feature-Free Syntax. Cambridge University Press, 2019.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

Boeckx, Cedric. Elementary Syntactic Structures : Prospects of a Feature-Free Syntax. Cambridge University Press, 2014.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
10

Ssempuuma, Jude. Morphological and Syntactic Feature Analysis of Ugandan English : Influence from Luganda, Runyankole-Rukiga, and Acholi-Lango. Lang GmbH, Internationaler Verlag der Wissenschaften, Peter, 2019.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
Plus de sources

Chapitres de livres sur le sujet "Syntactic feature"

1

Hristea, Florentina T. « Syntactic Dependency-Based Feature Selection ». Dans The Naïve Bayes Model for Unsupervised Word Sense Disambiguation, 35–53. Berlin, Heidelberg : Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-33693-5_4.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
2

Radziszewski, Adam, Adam Wardyński et Tomasz Śniatowski. « WCCL : A Morpho-syntactic Feature Toolkit ». Dans Text, Speech and Dialogue, 434–41. Berlin, Heidelberg : Springer Berlin Heidelberg, 2011. http://dx.doi.org/10.1007/978-3-642-23538-2_55.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

Baird, H. S. « Applications of Multidimensional Search to Structural Feature Identification ». Dans Syntactic and Structural Pattern Recognition, 137–49. Berlin, Heidelberg : Springer Berlin Heidelberg, 1988. http://dx.doi.org/10.1007/978-3-642-83462-2_9.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
4

Liu, Keqiang, Zhiqiang Yan, Yuquan Wang, Lijie Wen et Jianmin Wang. « Efficient Syntactic Process Difference Detection Using Flexible Feature Matching ». Dans Lecture Notes in Business Information Processing, 103–16. Cham : Springer International Publishing, 2014. http://dx.doi.org/10.1007/978-3-319-08222-6_8.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
5

Wu, Liang, Yuanchun Zhou, Fei Tan, Fenglei Yang et Jianhui Li. « Generating Syntactic Tree Templates for Feature-Based Opinion Mining ». Dans Advanced Data Mining and Applications, 1–12. Berlin, Heidelberg : Springer Berlin Heidelberg, 2011. http://dx.doi.org/10.1007/978-3-642-25856-5_1.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Szwabe, Andrzej, Paweł Misiorek, Jarosław Bąk et Michał Ciesielczyk. « Tensor-Based Syntactic Feature Engineering for Ontology Instance Matching ». Dans Artificial Intelligence and Soft Computing, 609–22. Cham : Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-59060-8_55.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Kicsi, András, László Vidács, Viktor Csuvik, Ferenc Horváth, Árpád Beszédes et Ferenc Kocsis. « Supporting Product Line Adoption by Combining Syntactic and Textual Feature Extraction ». Dans New Opportunities for Software Reuse, 148–63. Cham : Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-90421-4_10.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
8

Agrawal, Ruchi, et G. Ram Mohan Reddy. « Syntactic and Semantic Feature Extraction and Preprocessing to Reduce Noise in Bug Classification ». Dans Wireless Networks and Computational Intelligence, 329–39. Berlin, Heidelberg : Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-31686-9_39.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

Tomić, Olga Mišeska. « Introduction ». Dans Balkan Sprachbund Morpho-Syntactic Features, 1–33. Dordrecht : Springer Netherlands, 2006. http://dx.doi.org/10.1007/1-4020-4488-7_1.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
10

Tomić, Olga Mišeska. « Ethno-Historical Considerations ». Dans Balkan Sprachbund Morpho-Syntactic Features, 35–48. Dordrecht : Springer Netherlands, 2006. http://dx.doi.org/10.1007/1-4020-4488-7_2.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.

Actes de conférences sur le sujet "Syntactic feature"

1

Prasad, Lakshman, Alexei N. Skourikhine et Bernd R. Schlei. « Feature-based syntactic and metric shape recognition ». Dans International Symposium on Optical Science and Technology, sous la direction de Longin J. Latecki, David M. Mount et Angela Y. Wu. SPIE, 2000. http://dx.doi.org/10.1117/12.404825.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
2

Poulos, Marios. « Definition text's syntactic feature using stationarity control ». Dans 2017 8th International Conference on Information, Intelligence, Systems & Applications (IISA). IEEE, 2017. http://dx.doi.org/10.1109/iisa.2017.8316418.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

Zhan, Wenlian, et Zhulin Shen. « Syntactic structure feature analysis and classification method research ». Dans 2012 International Conference on Audio, Language and Image Processing (ICALIP). IEEE, 2012. http://dx.doi.org/10.1109/icalip.2012.6376787.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
4

Xu, Liheng, Kang Liu, Siwei Lai et Jun Zhao. « Product Feature Mining : Semantic Clues versus Syntactic Constituents ». Dans Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1 : Long Papers). Stroudsburg, PA, USA : Association for Computational Linguistics, 2014. http://dx.doi.org/10.3115/v1/p14-1032.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
5

Wang, Xuren. « FSSRE : Fusing Semantic Feature and Syntactic Dependencies Feature for threat intelligence Relation Extraction ». Dans The 33rd International Conference on Software Engineering and Knowledge Engineering. KSI Research Inc., 2021. http://dx.doi.org/10.18293/seke2021-088.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Kim, Minho, et Hyuk-Chul Kwon. « Lyrics-Based Emotion Classification Using Feature Selection by Partial Syntactic Analysis ». Dans 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2011. http://dx.doi.org/10.1109/ictai.2011.165.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Gamgarn Somprasertsri et Pattarachai Lalitrojwong. « Automatic product feature extraction from online product reviews using maximum entropy with lexical and syntactic features ». Dans 2008 IEEE International Conference on Information Reuse and Integration (2008 IRI). IEEE, 2008. http://dx.doi.org/10.1109/iri.2008.4583038.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
8

Nakazawa, Tsuneko. « An extended LR parsing algorithm for grammars using feature-based syntactic categories ». Dans the fifth conference. Morristown, NJ, USA : Association for Computational Linguistics, 1991. http://dx.doi.org/10.3115/977180.977193.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

Khaing, Ei Thwe, Myint Myint Thein et Myint Myint Lwin. « Stock Trend Extraction using Rule-based and Syntactic Feature-based Relationships between Named Entities ». Dans 2019 International Conference on Advanced Information Technologies (ICAIT). IEEE, 2019. http://dx.doi.org/10.1109/aitc.2019.8920986.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
10

Ogiela, Marek R., et Ryszard Tadeusiewicz. « Syntactic methods of shape feature description and its application in analysis of medical images ». Dans Electronic Imaging, sous la direction de Robert F. Erbacher, Philip C. Chen, Jonathan C. Roberts et Craig M. Wittenbrink. SPIE, 2000. http://dx.doi.org/10.1117/12.378909.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
Vous pouvez également être intéressé par les bibliographies sur le sujet « Syntactic feature » pour d’autres types de sources :
Articles de revues Thèses Livres
Nous offrons des réductions sur tous les plans premium pour les auteurs dont les œuvres sont incluses dans des sélections littéraires thématiques. Contactez-nous pour obtenir un code promo unique!

Vers la bibliographie