Academic literature on the topic 'Lexical relations'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Lexical relations.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Lexical relations"
1
Jackendoff, Ray, and Jenny Audring. "Morphological schemas." New Questions for the Next Decade 11, no. 3 (2016): 467–93. http://dx.doi.org/10.1075/ml.11.3.06jac.
Full textAbstract:
We propose a theory of the lexicon in which rules of grammar, encoded as declarative schemas, are lexical items containing variables. We develop a notation to encode precise relations among lexical items and show how this differs from the standard notion of inheritance. We also show how schemas can play both a generative role, acting as productive rules, and also a relational role, where they codify nonproductive but nevertheless prolific patterns within the lexicon. We then show how this theory of lexical relations can be embedded directly into a theory of lexical access and lexical processing, such that it can make direct contact with experimental findings.
2
Zhou, Jiayu, Shi Wang, and Cungen Cao. "Learning Hierarchical Lexical Hyponymy." International Journal of Cognitive Informatics and Natural Intelligence 4, no. 1 (2010): 98–114. http://dx.doi.org/10.4018/jcini.2010010106.
Full textAbstract:
Chinese information processing is a critical step toward cognitive linguistic applications like machine translation. Lexical hyponymy relation, which exists in some Eastern languages like Chinese, is a kind of hyponymy that can be directly inferred from the lexical compositions of concepts, and of great importance in ontology learning. However, a key problem is that the lexical hyponymy is so commonsense that it cannot be discovered by any existing acquisition methods. In this paper, we systematically define lexical hyponymy relationship, its linguistic features and propose a computational approach to semi-automatically learn hierarchical lexical hyponymy relations from a large-scale concept set, instead of analyzing lexical structures of concepts. Our novel approach discovered lexical hyponymy relation by examining statistic features in a Common Suffix Tree. The experimental results show that our approach can correctly discover most lexical hyponymy relations in a given large-scale concept set.
3
Miller, George, Christiane Fellbaum, Judy Kegl, and Katherine Miller. "WordNet: An Electronic Lexical Reference System Based on Theories of Lexical Memory." Revue québécoise de linguistique 17, no. 2 (2009): 181–212. http://dx.doi.org/10.7202/602632ar.
Full textAbstract:
Abstract This paper describes WordNet, an on-line lexical reference system whose design is based on psycholinguistic theories of human lexical organization and memory. English nouns, verbs, and adjectives are organized into synonym sets, each representing one underlying lexical concept. Synonym sets are then related via three principal conceptual relations: hyponymy, meronymy, and antonymy. Verbs are additionally specified for presupposition relations that hold among them, and for their most common semantic/syntactic frames. By attempting to mirror the organization of the mental lexicon, WordNet strives to serve the linguistically unsophisticated user.
4
Iskandarova, Sharifa Madalievna, and Dilafruzkhon Shukhratovna Rakhmatullaeva. "Associative Relations Between Lexical Units Of The Uzbek Language." American Journal of Social Science and Education Innovations 03, no. 03 (2021): 265–69. http://dx.doi.org/10.37547/tajssei/volume03issue03-39.
Full text
5
van Helden-Lankhaar, Marja. "A connection in lexical development." Annual Review of Language Acquisition 1 (October 19, 2001): 157–90. http://dx.doi.org/10.1075/arla.1.05hel.
Full textAbstract:
The relationship is examined between two different domains of lexical development: innovative compounding and access to abstract lexical relations. The creation of novel compounds as appropriate labels for novel concepts requires the accessibility of relatively abstract relations between word meanings in the mental lexicon. In a picture naming task in which novel concepts have to be labeled (e.g., a vehicle that can both sail and drive) children’s production of appropriate novel compounds (e.g., car-boat) increases with age. This compound production is, independently of age, related to children’s ability to access coordinate lexical relations (such as between cat and dog) in a contrastive word association task (‘a cat is not a...?’). It is proposed that this connection between innovative compounding and access to coordinate relations is cognitive in nature and involves a common ability for lexical comparisons. Innovative compounding reflects comparison ‘on the spot’ between the novel concept and available related word meaning knowledge, and contrastive coordinate production reflects the results of developmentally earlier comparison processes evoked by adult contrastive input.
6
Setianingrum, Diah Ayu, Januarius Mujiyanto, and Sri Wuli Fitriati. "The Use of Semantic Lexical Relation in Rowling’s “Harry Potter and the Deathly Hallowsâ€." English Education Journal 11, no. 1 (2021): 159–65. http://dx.doi.org/10.15294/eej.v11i1.35892.
Full textAbstract:
Semantics is the study of words’ meaning. One of the branches of semantics is a lexical relation study. It refers to the relationship between the meaning of words. The focus of this article is the explanation of the use of three types of lexical relations: synonymy, antonymy and hyponymy in the Rowling’s novel “Harry Potter and the Deathly Hallowsâ€. The study aims to explain the use of the elements or the three types of semantics lexical relation appeared in that novel.This study employed qualitative research in the form of content analysis which deeply investigates the meanings in the novel. The units of analysis are words that appeared in the novel, taken from the whole chapters of the novel. Therefore, the object is semantics lexical relations comprising three types of lexical relations: synonymy, antonymy and hyponymy.The findings show that each type of lexical relation is interconnected with one another. The most dominant type that is used by the author of the novel is antonymy. There were 148 out of 319 items, followed by synonymy with 97 finding items and then hyponymy with 26 finding items.This current study hopefully can enhance the teacher or lecturers and the students English Language Education to involve the semantics lexical relation. Moreover, the findings and discussions can be applied in English Language Education Study Program, specifically in the semantics subject. The implications of lexical relation could be found not only in an English textbook but also in literature work such as novel, poetry, poem, even in play or drama, which is the subject that is required to learn by every single student.
7
Shimotori, Misuzu. "Conceptual relations in the semantic domain of Swedish dimensional adjectives." European Journal of Scandinavian Studies 46, no. 2 (2016): 270–88. http://dx.doi.org/10.1515/ejss-2016-0023.
Full textAbstract:
Abstract In the conventional study of lexical semantics, adjectives are not considered likely to have a hierarchical relation, such as a meronymic (part-whole) relation, to each other. The most possible lexical relations among adjectives are antonymy and synonymy. In this study, however, I assume that meronomic relations between internal members of dimensional adjectives (e. g. big, long, deep) are conceptually possible from an ontological point of view. By using a semantic task, i. e. anaphora resolution, I draw the following conclusion: dimensional adjectives themselves have no meronymic relation to each other. However, restricting our discussion to the usage of Swedish dimensional adjectives in modifying concrete entities, the conceptual relations between the general term, e. g. BIG,1I use capital letters to indicate concepts throughout this essay. Lexical items are written in italics. and specific terms, e. g. LONG, DEEP, are mentally organized in a part-whole relation and thus in a meronomic structure. When applied to the whole expression which is a concept of a big entity, such as BIG CUP, there are meronomic relations between concepts of the big entity and its parts, e. g. BIG CUP – DEEP CUP.
8
Arora, Kushal, Aishik Chakraborty, and Jackie C. K. Cheung. "Learning Lexical Subspaces in a Distributional Vector Space." Transactions of the Association for Computational Linguistics 8 (July 2020): 311–29. http://dx.doi.org/10.1162/tacl_a_00316.
Full textAbstract:
In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics. We inject knowledge about lexical-semantic relations into distributional word embeddings by defining subspaces of the distributional vector space in which a lexical relation should hold. Our framework can handle symmetric attract and repel relations (e.g., synonymy and antonymy, respectively), as well as asymmetric relations (e.g., hypernymy and meronomy). In a suite of intrinsic benchmarks, we show that our model outperforms previous approaches on relatedness tasks and on hypernymy classification and detection, while being competitive on word similarity tasks. It also outperforms previous systems on extrinsic classification tasks that benefit from exploiting lexical relational cues. We perform a series of analyses to understand the behaviors of our model. 1 Code available at https://github.com/aishikchakraborty/LexSub .
9
Boelens, Harrie, and Jeroen Mollers. "In Search of Competition between Lexical and Grammatical Growth." Psychological Reports 104, no. 2 (2009): 407–17. http://dx.doi.org/10.2466/pr0.104.2.407-417.
Full textAbstract:
Relations between lexical and grammatical growth were examined in a Dutch boy from age 1:0 to 2:6. The overall shape of lexical growth was a pronounced increase in rate until age 2:2 approximately and a slight decrease in rate thereafter. Two measures of early grammatical growth (the percentage of obligatory plural contexts in which plurals were used and mean length of utterances) reached high levels well before the age of 2:2. Further, there was no evidence for a relation between the change from one week to the next in the number of new words and the change from one week to the next on the two grammatical measures. Thus, no evidence for competition between lexical and grammatical growth was found on both a larger and a smaller time scale. Patterns of lexical and grammatical growth suggestive of competition may be especially likely when the productive lexicon grows very fast initially.
10
Bouveret, Myriam. "Fonctions lexicales pour le typage de relations syntagmatiques et paradigmatiques." Terminology 12, no. 2 (2006): 235–59. http://dx.doi.org/10.1075/term.12.2.05mor.
Full textAbstract:
In this paper, we present the conversion of a specialized dictionary of bioindustries by means of Lexical Functions (Mel’čuk et al. 1984, 1988, 1992, 1999 ; Mel’čuk et al. 1995). The dictionary is based on semantic derivation as described in Explanatory and Combinatorial Lexicology, and explores compatibilities with lexico-syntactic descriptions as in Fillmore (1977, 2003) and Levin (1993) in order to assign circumstantial Lexical Functions. We first describe semantic relations such as hyperonymy, hyponymy, synonymy, antonymy and several cases of meronymy ; subsequently, we discuss verbs and predicative relations with reference to arguments and adjuncts. Finally, we explore the possibility of pursuing the research with an additional entry for definitions.
Dissertations / Theses on the topic "Lexical relations"
1
Morlane-Hondère, François. "Une approche linguistique de l'évaluation des ressources extraites par analyse distributionnelle automatique." Phd thesis, Université Toulouse le Mirail - Toulouse II, 2013. http://tel.archives-ouvertes.fr/tel-00937926.
Full textAbstract:
Dans cette thèse, nous abordons du point de vue linguistique la question de l'évaluation des bases lexicales extraites par analyse distributionnelle automatique (ADA). Les méthodes d'évaluation de ces ressources qui sont actuellement mises en œuvre (comparaison à des lexiques de référence, évaluation par la tâche, test du TOEFL...) relèvent en effet d'une approche quantitative des données qui ne laisse que peu de place à l'interprétation des rapprochements générés. De ce fait, les conditions qui font que certains couples de mots sont extraits alors que d'autres ne le sont pas restent mal connues. Notre travail vise une meilleure compréhension des fonctionnements en corpus qui régissent les rapprochements distributionnels. Pour cela, nous avons dans un premier temps adopté une approche quantitative qui a consisté à comparer plusieurs ressources distributionnelles calculées sur des corpus différents à des lexiques de références (le Dictionnaire électronique des synonymes du CRISCO et le réseau lexical JeuxDeMots). Cette étape nous a permis, premièrement, d'avoir une estimation globale du contenu de nos ressources, et, deuxièmement, de sélectionner des échantillons de couples de mots à étudier d'un point de vue qualitatif. Cette deuxième étape constitue le cœur de la thèse. Nous avons choisi de nous focaliser sur les relations lexico-sémantiques que sont la synonymie, l'antonymie, l'hyperonymie et la méronymie, que nous abordons en mettant en place quatre protocoles différents. En nous appuyant sur les relations contenues dans les lexiques de référence, nous avons comparé les propriétés distributionnelles des couples de synonymes/antonymes/hyperonymes/méronymes qui ont été extraits par l'ADA avec celles des couples qui ne l'ont pas été. Nous mettons ainsi au jour plusieurs phénomènes qui favorisent ou bloquent la substituabilité des couples de mots (donc leur extraction par l'ADA). Ces phénomènes sont considérés au regard de paramètres comme la nature du corpus qui a permis de générer les bases distributionnelles étudiées (corpus encyclopédique, journalistique ou littéraire) ou les limites des lexiques de référence. Ainsi, en même temps qu'il questionne les méthodes d'évaluation des bases distributionnelles actuellement employées, ce travail de thèse illustre l'intérêt qu'il y a à considérer ces ressources comme des objets d'études linguistiques à part entière. Les bases distributionnelles sont en effet le résultat d'une mise en œuvre à grande échelle du principe de substituabilité, ce qui en fait un matériau de choix pour la description des relations lexico-sémantiques.
2
Yuret, Deniz. "Discovery of linguistic relations using lexical attraction." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/9961.
Full text
3
Fernando, Samuel. "Enriching lexical knowledge bases with encyclopedic relations." Thesis, University of Sheffield, 2013. http://etheses.whiterose.ac.uk/4081/.
Full textAbstract:
Lexical knowledge bases, such as WordNet, have been shown to be useful in a wide range of language processing applications. However WordNet lacks certain information, such as topical relations between synsets. This thesis addresses this problem by enriching WordNet using information derived from Wikipedia. The approach consists of mapping concepts in WordNet to corresponding articles in Wikipedia. This is done using a three stage approach. First a set of possible candidate articles is retrieved for each WordNet concept. This is done by searching using the article title, and also by searching the full text using an IR engine. Secondly, text similarity scores are used to select the best match from the candidate articles. Finally, the mappings are refined using information from Wikipedia links to give a set of high quality matches. The mappings are evaluated using a manually annotated gold standard set of synset-article mappings. The annotation process indicates that the majority of synsets have a good matching article. The refined mappings are shown to have precision of 88.2\%. The mappings are then used to enrich relations in WordNet using Wikipedia links. The enriched WordNet is then used with a knowledge based Word Sense Disambiguation system. Evaluations are performed on the Semcor 3.0 corpus. Adding the new relations improves performance significantly over the WordNet baseline, demonstrating the usefulness of the mappings on an extrinsic task.
4
Jousse, Anne-Laure. "Modèle de structuration des relations lexicales fondé sur le formalisme des fonctions lexicales." Thèse, Paris 7, 2010. http://hdl.handle.net/1866/4347.
Full textAbstract:
Cette thèse porte sur l’élaboration d’un modèle de structuration des relations lexicales, fondé sur les fonctions lexicales de la Théorie Sens-Texte [Mel’cuk, 1997]. Les relations lexicales considérées sont les dérivations sémantiques et les collocations telles qu’elles sont définies dans le cadre de la Lexicologie Explicative et Combinatoire [Mel’cuk et al., 1995]. En partant du constat que ces relations lexicales ne sont pas décrites ni présentées de façon satisfaisante dans les bases de données lexicales, nous posons la nécessité d’en créer un modèle de structuration.
Nous justifions l’intérêt de créer un système de fonctions lexicales puis détaillons les quatre perspectives du système que nous avons mises au point : une perspective sémantique, une perspective axée sur la combinatoire des éléments d’une relation lexicale, une perspective centrée sur leurs parties du discours, ainsi qu’une perspective mettant en avant l’élément sur lequel se focalise la relation. Le système intègre l’ensemble des fonctions lexicales, y compris les fonctions lexicales non standard, dont nous proposons une normalisation de l’encodage.
Le système a été implémenté dans la base de données lexicale du DiCo. Nous
présentons trois applications dans lesquelles il peut être exploité. Premièrement, il est possible d’en dériver des interfaces de consultation pour les bases de données lexicales de type DiCo. Le système peut également être directement consulté en tant qu’assistant à l’encodage des relations lexicales. Enfin, il sert de référence pour effectuer un certain nombre de calculs sur les informations lexicographiques, qui pourront, par la suite, être implémentés pour automatiser la rédaction de certains champs de fiches lexicographiques.<br>This thesis proposes a model for structuring lexical relations, based on the concept of lexical functions (LFs) proposed in Meaning-Text Theory [Mel’cuk, 1997]. The lexical relations taken into account include semantic derivations and collocations as defined within this theoretical framework, known as Explanatory and Combinatorial Lexicology [Mel’cuk et al., 1995]. Considering the assumption that lexical relations are neither encoded nor made available in lexical databases in an entirely satisfactory manner, we assume the necessity of designing a new model for structuring them.
First of all, we justify the relevance of devising a system of lexical functions rather than a simple classification. Next, we present the four perspectives developped in the system: a semantic perspective, a combinatorial one, another one targetting the parts of speech of the elements involved in a lexical relation, and, finally, a last one emphasizing which element of the relation is focused on. This system covers all LFs, even non-standard ones, for which we have proposed a normalization of the encoding.
Our system has already been implemented into the DiCo relational database. We
propose three further applications that can be developed from it. First, it can be used to build browsing interfaces for lexical databases such as the DiCo. It can also be directly consulted as a tool to assist lexicographers in encoding lexical relations by means of lexical functions. Finally, it constitutes a reference to compute lexicographic information which will, in future work, be implemented in order to automatically fill in some fields within the entries in lexical databases.<br>Thèse réalisée en cotutelle avec l'Université Paris Diderot (Paris 7)
5
Necşulescu, Silvia. "Automatic acquisition of lexical-semantic relations: gathering information in a dense representation." Doctoral thesis, Universitat Pompeu Fabra, 2016. http://hdl.handle.net/10803/374234.
Full textAbstract:
Lexical-semantic relationships between words are key information for many NLP tasks, which require this knowledge in the form of lexical resources. This thesis addresses the acquisition of lexical-semantic relation instances. State of the art systems rely on word pair representations based on patterns of contexts where two related words co-occur to detect their relation. This approach is hindered by data sparsity: even when mining very large corpora, not every semantically related word pair co-occurs or not frequently enough.
In this work, we investigate novel representations to predict if two words hold a lexical-semantic relation. Our intuition was that these representations should contain information about word co-occurrences combined with information about the meaning of words involved in the relation. These two sources of information have to be the basis of a generalization strategy to be able to provide information even for words that do not co-occur.<br>Les relacions lexicosemàntiques entre paraules són una informació clau per a moltes tasques del PLN, què requereixen aquest coneixement en forma de recursos lingüístics. Aquesta tesi tracta l’adquisició d'instàncies lexicosemàntiques. Els sistemes actuals utilitzen representacions basades en patrons dels contextos en què dues paraules coocorren per detectar la relació que s'hi estableix. Aquest enfocament s'enfronta a problemes de falta d’informació: fins i tot en el cas de treballar amb corpus de grans dimensions, hi haurà parells de paraules relacionades que no coocorreran, o no ho faran amb la freqüència necessària. Per tant, el nostre objectiu principal ha estat proposar noves representacions per predir si dues paraules estableixen una relació lexicosemàntica.
La intuïció era que aquestes representacions noves havien de contenir informació sobre patrons dels contextos, combinada amb informació sobre el significat de les paraules implicades en la relació. Aquestes dues fonts d'informació havien de ser la base d'una estratègia de generalització que oferís informació fins i tot quan les dues paraules no coocorrien.
6
Coventry, Kenneth Richmond. "Spatial prepositions and functional relations : the case for minimally specified lexical entries." Thesis, University of Edinburgh, 1993. http://hdl.handle.net/1842/26414.
Full textAbstract:
In this thesis we present a minimally specified approach to the lexical entries for spatial prepositions based on the recognition of the importance of functional relations. We begin by introducing the problem of separating our senses of a lexeme from occurrences of a lexeme, and with a consideration of methods of sense delineation, including ambiguity tests. We then consider classical approaches to the lexical entries of prepositions which favour minimal specification of lexical entries, and compare them to cognitive linguistic accounts which favour full specification of lexical entries. It is argued that classical accounts have problems with case accountability, while cognitive linguistic accounts are based on a misinterpretation of prototype theory. We demonstrate that the accounts are very similar in that they delineate senses in terms of different geometric relations in the world. Functional relations are introduced as an alternative way of understanding spatial relations. It is argued that what is important about objects is how they interact with each other, that is, the <i>functional relations</i> between objects. The work of Garrod and Sanford (1989) and Talmy (1988) is considered in this context, and is developed to deal more adequately with case accountability. A number of experimental studies are reported which demonstrate the existence of functional relations, and cast doubt on ambiguity tests as valid methods of sense delineation. It is proposed that a spatial preposition can be said to have two senses if a language user has a motivated reason for distinguishing between two types of relation. Evidence is provided for a distinction between spatial prepositions which involve functional components, and those that involve purely geometric components. First language acquisition evidence is reviewed which suggests that prepositions involving functional relations are learned first.
7
Conrath, Juliette. "Unsupervised extraction of semantic relations using discourse information." Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30202/document.
Full textAbstract:
La compréhension du langage naturel repose souvent sur des raisonnements de sens commun, pour lesquels la connaissance de relations sémantiques, en particulier entre prédicats verbaux, peut être nécessaire. Cette thèse porte sur la problématique de l'utilisation d'une méthode distributionnelle pour extraire automatiquement les informations sémantiques nécessaires à ces inférences de sens commun. Des associations typiques entre des paires de prédicats et un ensemble de relations sémantiques (causales, temporelles, de similarité, d'opposition, partie/tout) sont extraites de grands corpus, par l'exploitation de la présence de connecteurs du discours signalant typiquement ces relations. Afin d'apprécier ces associations, nous proposons plusieurs mesures de signifiance inspirées de la littérature ainsi qu'une mesure novatrice conçue spécifiquement pour évaluer la force du lien entre les deux prédicats et la relation. La pertinence de ces mesures est évaluée par le calcul de leur corrélation avec des jugements humains, obtenus par l'annotation d'un échantillon de paires de verbes en contexte discursif. L'application de cette méthodologie sur des corpus de langue française et anglaise permet la construction d'une ressource disponible librement, Lecsie (Linked Events Collection for Semantic Information Extraction). Celle-ci est constituée de triplets: des paires de prédicats associés à une relation; à chaque triplet correspondent des scores de signifiance obtenus par nos mesures.Cette ressource permet de dériver des représentations vectorielles de paires de prédicats qui peuvent être utilisées comme traits lexico-sémantiques pour la construction de modèles pour des applications externes. Nous évaluons le potentiel de ces représentations pour plusieurs applications. Concernant l'analyse du discours, les tâches de la prédiction d'attachement entre unités du discours, ainsi que la prédiction des relations discursives spécifiques les reliant, sont explorées. En utilisant uniquement les traits provenant de notre ressource, nous obtenons des améliorations significatives pour les deux tâches, par rapport à plusieurs bases de référence, notamment des modèles utilisant d'autres types de représentations lexico-sémantiques. Nous proposons également de définir des ensembles optimaux de connecteurs mieux adaptés à des applications sur de grands corpus, en opérant une réduction de dimension dans l'espace des connecteurs, au lieu d'utiliser des groupes de connecteurs composés manuellement et correspondant à des relations prédéfinies. Une autre application prometteuse explorée dans cette thèse concerne les relations entre cadres sémantiques (semantic frames, e.g. FrameNet): la ressource peut être utilisée pour enrichir cette structure par des relations potentielles entre frames verbaux à partir des associations entre leurs verbes. Ces applications diverses démontrent les contributions prometteuses amenées par notre approche permettant l'extraction non supervisée de relations sémantiques<br>Natural language understanding often relies on common-sense reasoning, for which knowledge about semantic relations, especially between verbal predicates, may be required. This thesis addresses the challenge of using a distibutional method to automatically extract the necessary semantic information for common-sense inference. Typical associations between pairs of predicates and a targeted set of semantic relations (causal, temporal, similarity, opposition, part/whole) are extracted from large corpora, by exploiting the presence of discourse connectives which typically signal these semantic relations. In order to appraise these associations, we provide several significance measures inspired from the literature as well as a novel measure specifically designed to evaluate the strength of the link between the two predicates and the relation. The relevance of these measures is evaluated by computing their correlations with human judgments, based on a sample of verb pairs annotated in context. The application of this methodology to French and English corpora leads to the construction of a freely available resource, Lecsie (Linked Events Collection for Semantic Information Extraction), which consists of triples: pairs of event predicates associated with a relation; each triple is assigned significance scores based on our measures. From this resource, vector-based representations of pairs of predicates can be induced and used as lexical semantic features to build models for external applications. We assess the potential of these representations for several applications. Regarding discourse analysis, the tasks of predicting attachment of discourse units, as well as predicting the specific discourse relation linking them, are investigated. Using only features from our resource, we obtain significant improvements for both tasks in comparison to several baselines, including ones using other representations of the pairs of predicates. We also propose to define optimal sets of connectives better suited for large corpus applications by performing a dimension reduction in the space of the connectives, instead of using manually composed groups of connectives corresponding to predefined relations. Another promising application pursued in this thesis concerns relations between semantic frames (e.g. FrameNet): the resource can be used to enrich this sparse structure by providing candidate relations between verbal frames, based on associations between their verbs. These diverse applications aim to demonstrate the promising contributions provided by our approach, namely allowing the unsupervised extraction of typed semantic relations
8
Popa, Diana-Nicoleta. "From lexical towards contextualized meaning representation." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAM037.
Full textAbstract:
Les représentations des mots sont à la base du plupart des systèmes modernes pour le traitement automatique du langage, fournissant des résultats compétitifs. Cependant, d'importantes questions se posent concernant les défis auxquels ils sont confrontés pour faire face aux phénomènes complexes du langage naturel et leur capacité à saisir la variabilité du langage naturel.Pour mieux gérer les phénomènes complexes du langage, de nombreux travaux ont été menées pour affiner les représentations génériques de mots ou pour créer des représentations spécialisées. Bien que cela puisse aider à distinguer la similarité sémantique des autres types de relations sémantiques, il peut ne pas suffire de modéliser certains types de relations, telles que les relations logiques d'implication ou de contradiction.La première partie de la thèse étudie l'encodage de la notion d'implication textuelle dans un espace vectoriel en imposant l'inclusion d'information. Des opérateurs d'implication sont ensuite développées et le cadre proposé peut être utilisé pour réinterpréter un modèle existant de la sémantique distributionnelle. Des évaluations sont fournies sur la détection d'hyponymie en tant que une instance d'implication lexicale.Un autre défi concerne la variabilité du langage naturel et la nécessité de désambiguïser les unités lexicales en fonction du contexte dans lequel elles apparaissent. Les représentations génériques de mots ne réussissent pas à elles seules, des architectures différentes étant généralement utilisées pour aider à la désambiguïsation. Étant donné que les représentations de mots sont construites à partir de statistiques de cooccurrence sur de grands corpus et qu’elles reflètent ces statistiques, elles fournissent une seule représentation pour un mot donné, malgré ses multiples significations. Même dans le cas de mots monosémiques, cela ne fait pas la distinction entre les différentes utilisations d’un mot en fonction de son contexte.Dans ce sens, on pourrait se demander s'il est possible d'exploiter directement les informations linguistiques fournies par le contexte d'un mot pour en ajuster la représentation. Ces informations seraient-elles utiles pour créer une représentation enrichie du mot dans son contexte? Et si oui, des informations de nature syntaxique peuvent-elles aider au processus ou le contexte local suffit? On peux donc examiner si les représentations génériques des mots et la manière dont elles se combinent peut suffire à construire des représentations plus précises.Dans la deuxième partie de la thèse, nous étudions une façon d’incorporer la connaissance contextuelle dans les représentations de mots eux-mêmes, en exploitant les informations provenant de l’analyse de dépendance de phrase ainsi que les informations de voisinage local. Nous proposons des représentations de mots contextualisées sensibles à la syntaxe (SATokE) qui capturent des informations linguistiques spécifiques et encodent la structure de la phrase dans leurs représentations. Cela permet de passer des représentations de type générique (invariant du contexte) à des représentations spécifiques (tenant compte du contexte). Alors que la syntaxe était précédemment considérée pour les représentations de mots, ses avantages n'ont peut-être pas été entièrement évalués au-delà des modèles qui exploitent ces informations à partir de grands corpus.Les représentations obtenues sont évaluées sur des tâches de compréhension du langage naturel: classification des sentiments, détection de paraphrases, implication textuelle et analyse du discours. Nous démontrons empiriquement la supériorité de ces représentations par rapport aux représentations génériques et contextualisées des mots existantes.Le travail proposé dans la présente thèse contribue à la recherche dans le domaine de la modélisation de phénomènes complexes tels que l'implication textuelle, ainsi que de la variabilité du langage par le biais de la proposition de représentations contextualisés<br>Continuous word representations (word type embeddings) are at the basis of most modern natural language processing systems, providing competitive results particularly when input to deep learning models. However, important questions are raised concerning the challenges they face in dealing with the complex natural language phenomena and regarding their ability to capture natural language variability.To better handle complex language phenomena, much work investigated fine-tuning the generic word type embeddings or creating specialized embeddings that satisfy particular linguistic constraints. While this can help distinguish semantic similarity from other types of semantic relatedness, it may not suffice to model certain types of relations between texts such as the logical relations of entailment or contradiction.The first part of the thesis investigates encoding the notion of entailment within a vector space by enforcing information inclusion, using an approximation to logical entailment of binary vectors. We further develop entailment operators and show how the proposed framework can be used to reinterpret an existing distributional semantic model. Evaluations are provided on hyponymy detection as an instance of lexical entailment.Another challenge concerns the variability of natural language and the necessity to disambiguate the meaning of lexical units depending on the context they appear in. For this, generic word type embeddings fall short of being successful by themselves, with different architectures being typically employed on top to help the disambiguation. As type embeddings are constructed from and reflect co-occurrence statistics over large corpora, they provide one single representation for a given word, regardless of its potentially numerous meanings. Furthermore, even given monosemous words, type embeddings do not distinguish between the different usages of a word depending on its context.In that sense, one could question if it is possible to directly leverage available linguistic information provided by the context of a word to adjust its representation. Would such information be of use to create an enriched representation of the word in its context? And if so, can information of syntactic nature aid in the process or is local context sufficient? One could thus investigate whether looking at the representations of the words within a sentence and the way they combine with each-other can suffice to build more accurate token representations for that sentence and thus facilitate performance gains on natural language understanding tasks.In the second part of the thesis, we investigate one possible way to incorporate contextual knowledge into the word representations themselves, leveraging information from the sentence dependency parse along with local vicinity information. We propose syntax-aware token embeddings (SATokE) that capture specific linguistic information, encoding the structure of the sentence from a dependency point of view in their representations. This enables moving from generic type embeddings (context-invariant) to specific token embeddings (context-aware). While syntax was previously considered for building type representations, its benefits may have not been fully assessed beyond models that harvest such syntactical information from large corpora.The obtained token representations are evaluated on natural language understanding tasks typically considered in the literature: sentiment classification, paraphrase detection, textual entailment and discourse analysis. We empirically demonstrate the superiority of the token representations compared to popular distributional representations of words and to other token embeddings proposed in the literature.The work proposed in the current thesis aims at contributing to research in the space of modelling complex phenomena such as entailment as well as tackling language variability through the proposal of contextualized token embeddings
9
Xavier, Vanessa Regina Duarte. "Conexões léxico-culturais sobre as minas goianas setecentistas no Livro para servir no registro do caminho novo de Parati." Universidade de São Paulo, 2012. http://www.teses.usp.br/teses/disponiveis/8/8142/tde-29082012-100504/.
Full textAbstract:
Esta tese tem como propósito ratificar que o estudo lexical de manuscritos pertencentes ao códice intitulado Livro para servir no registro do caminho novo de Parati Thomé Ignácio da Costa Mascarenhas (1724-1762) muito revela a respeito da formação sociocultural da então recém-criada Capitania de Goiás, durante o ciclo do ouro. Para tanto, realizou-se a edição semidiplomática de noventa e dois documentos escritos de 1751 a 1753 em Vila Boa de Goiás, uma vez que estes abordam aspectos variados da administração, economia, política, religião, cultura, assim como da estrutura jurídica e militar local. Conferiu-se rigor à aplicação dos critérios de edição, com vistas a assegurar a sua fidedignidade e, consequentemente, de toda a pesquisa. Foram inventariados os substantivos, adjetivos e verbos para a elaboração de um Índice de Frequência e de Ocorrências dos Itens Lexicais, à luz do produzido por Ferreira et al. (2005), a fim de se obter o vocabulário empregado no corpus e de mapear os principais assuntos abordados, correlacionando-os com a frequência de uso das lexias. Procedeu-se, então, à estruturação e análise dos campos lexicais mais representativos das temáticas do corpus, com base em aspectos histórico-sociais da Capitania goiana, tendo em vista que o léxico é o nível da língua que mais se conecta ao universo extralinguístico (BIDERMAN, 1981; SAPIR, 1961). A composição dos campos lexicais baseou-se nos princípios da semântica estrutural, especificamente em teóricos como Coseriu (1977), Geckeler (1976) e Vilela (1979), levando em conta as relações semânticas entre os itens lexicais e os arquilexemas dos campos, mais especificamente, a sinonímia, a antonímia, a meronímia e a hiponímia, identificando-se também os casos de homonímia e de polissemia. Os resultados dessa pesquisa apontam que o estudo dos campos lexicais a partir das associações semânticas entre seus membros não pode prescindir da consideração do universo discursivo, bem como do contexto sociocultural no qual se fundamentam, haja vista que os significados resultam do processamento cognitivo das experiências físicas, biológicas e sociais.<br>This thesis aims to ratify that lexical study of manuscripts belonging to the codex titled Livro para servir no registro do caminho novo de Parati Thomé Ignácio da Costa Mascarenhas (1724-1762) reveals much about the socio-cultural formation of the newly created Capitania de Goiás, during the cycle of the gold. To this end, did realized the semi-diplomatic edition of ninety-two documents written from 1751 to 1753 in Vila Boa de Goiás, since that approach different aspects of administration, economy, politics, religion, culture, and of the regional legal and military structure. Gave up rigorous application of criteria for editing, in order to ensure its reliability and, consequently, of all the research. Were inventoried the nouns, adjectives and verbs for the preparation of an Index of Frequency and Occurrences of Lexical Items, in the light of that produced by Ferreira et al. (2005), in order to get the vocabulary used in the corpus and mapping the main subjects approached, by correlating them with the frequency of use of the lexias. Proceeded, then, to structuring and analysis of lexical fields more representative of the themes of the corpus, based on historical and social aspects Capitania de Goiás, given that the lexicon is the level of language that connects more to the extralinguistic universe ( BIDERMAN, 1981; SAPIR, 1961). The composition of lexical fields was based on the principles of structural semantics, specifically in theoretical that Coseriu (1977), Geckeler (1976) and Vilela (1979), taking into account the semantic relationships between lexical items and arquilexemas of the fields, more specifically, the synonymy, the antonymy, the meronymy and the hyponymy, identifying the cases of homonymy and polysemy. The results of this study indicate that the study of lexical fields on semantic associations among its members cant escape of the consideration of the universe of discourse, and the sociocultural context in which they are based, given that the meanings result from cognitive processing of physical, biological and social experiences.
10
Neff, Kathryn Joan Eggers. "Neural net models of word representation : a connectionist approach to word meaning and lexical relations." Virtual Press, 1991. http://liblink.bsu.edu/uhtbin/catkey/832999.
Full textAbstract:
This study examines the use of the neural net paradigm as a modeling tool to represent word meanings. The neural net paradigm, also called "connectionism" and "parallel distributed processing," provides a new metaphor and vocabulary for representing the structure of the mental lexicon. As a research method applied to the componential analysis of word meanings, the neural net approach has one primary advantage over the traditional introspective method: freedom from the investigator's personal biases.The connectionist method is illustrated in this thesis with an extensive examination of the meanings of the words "cup" and "mug." These words have been studied previously by Labov (1973), Wierzbicka (1985), Andersen (1975), and Kempton (1978), using very different methods.The neural net models developed in this study are based on empirical data acquired through interviews with nine informants who classified 37 objects, 37 photographs, and 37 line drawings as "cups," "mugs," or "neither." These responses were combined with a data file representing the coded attributes of each object, to construct neural net models which reflect each informant's classification process.In the neural net models, the "cup" and "mug" features are interconnected with positive and negative weights that represent the association strengths of the features. When the connection weights are set so that they reflect the informants' responses, the neural net models can account for the extreme discrepancies in object-naming among informants, and the models can also account for the inconsistent classifications of each individual informant with respect to the mode of presentation (drawing, photograph, or actual object). Further, the neural net modelscan predict classifications for novel objects with an accuracy varying from 82% to 100%.By examining the connection weight patterns within the neural net model, it is possible to discover the "cup" and "mug" features which are most salient for each informant, and for the informants collectively. This analysis shows that each informant has acquired internal meanings for the words "cup" and "mug" which are unique to the individual, although there is considerable overlap with respect to the most salient features.<br>Department of English
Books on the topic "Lexical relations"
1
Koenig, Jean-Pierre. Lexical relations. Center for the Study of Language and Information, 1999.
Find full text
2
Storjohann, Petra, ed. Lexical-Semantic Relations. John Benjamins Publishing Company, 2010. http://dx.doi.org/10.1075/lis.28.
Full text
3
Gunnar, Persson, ed. Facets, phases, and foci: Studies in lexical relations in English. Universitetet i Umeå, 1986.
Find full text
5
Dubinsky, Stanley. A bibliography of relational grammar through May 1987 with selected titles on lexical functional grammar. Indiana University Linguistics Club, 1987.
Find full text
6
Dubinsky, Stanley. A bibliography on relational grammar through May 1987: With selected titles on lexical-functional grammar. Indiana University Linguistics Club, 1987.
Find full text
7
M, Evans Paul, ed. The Asia-Pacific security lexicon. 2nd ed. Institute of Southeast Asian Studies, 2007.
Find full text
8
Capie, David H. The Asia-Pacific security lexicon. Institute of Southeast Asian Studies, 2002.
Find full text
9
1940-, Abu-Zayed Ziad, and Rubinstein Danny, eds. The West Bank handbook: A political lexicon. Jerusalem Post, 1986.
Find full text
10
Linguistic theory and adult second language acquisition: On the relation between the lexicon and the syntax. P. Lang, 2000.
Find full textBook chapters on the topic "Lexical relations"
1
Cann, Ronnie. "6. Sense relations." In Semantics - Lexical Structures and Adjectives, edited by Claudia Maienborn, Klaus von Heusinger, and Paul Portner. De Gruyter, 2019. http://dx.doi.org/10.1515/9783110626391-006.
Full text
2
Renouf, Antoinette. "Lexical signals of word relations." In Patterns of Text. John Benjamins Publishing Company, 2001. http://dx.doi.org/10.1075/z.107.04ren.
Full text
3
Fellbaum, Christiane. "Semantics via Conceptual and Lexical Relations." In Breadth and Depth of Semantic Lexicons. Springer Netherlands, 1999. http://dx.doi.org/10.1007/978-94-017-0952-1_12.
Full text
4
Voorhees, Ellen M. "Query Expansion using Lexical-Semantic Relations." In SIGIR ’94. Springer London, 1994. http://dx.doi.org/10.1007/978-1-4471-2099-5_7.
Full text
5
Maurel, Denis, and Béatrice Bouchou-Markhoff. "Prolmf: A Multilingual Dictionary of Proper Names and their Relations." In LMF Lexical Markup Framework. John Wiley & Sons, Inc., 2013. http://dx.doi.org/10.1002/9781118712696.ch5.
Full text
6
Gómez, Antonio García. "Lexical Encoding of Gender Relations and Identities." In Gender Perspectives on Vocabulary in Foreign and Second Languages. Palgrave Macmillan UK, 2010. http://dx.doi.org/10.1057/9780230274938_11.
Full text
7
Kunze, Claudia, and Lothar Lemnitzer. "Lexical-semantic and conceptual relations in GermaNet." In Lingvisticæ Investigationes Supplementa. John Benjamins Publishing Company, 2010. http://dx.doi.org/10.1075/lis.28.10kun.
Full text
8
Amaro, Raquel, Sara Mendes, and Palmira Marrafa. "Lexical-Conceptual Relations as Qualia Role Encoders." In Text, Speech and Dialogue. Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-15760-8_5.
Full text
9
Bannour, Nesrine, Gaël Dias, Youssef Chahir, and Houssam Akhmouch. "Patch-Based Identification of Lexical Semantic Relations." In Lecture Notes in Computer Science. Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-45439-5_9.
Full text
10
Balikas, Georgios, Gaël Dias, Rumen Moraliyski, Houssam Akhmouch, and Massih-Reza Amini. "Learning Lexical-Semantic Relations Using Intuitive Cognitive Links." In Lecture Notes in Computer Science. Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-15712-8_1.
Full textConference papers on the topic "Lexical relations"
1
Huang, Chu-Ren, I.-Ju E. Tseng, and Dylan B. S. Tsai. "Translating lexical semantic relations." In COLING-02. Association for Computational Linguistics, 2002. http://dx.doi.org/10.3115/1118735.1118741.
Full text
2
Wang, Chengyu, Xiaofeng He, and Aoying Zhou. "SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings." In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/p19-1169.
Full text
3
Hindle, Donald, and Mats Rooth. "Structural ambiguity and lexical relations." In the 29th annual meeting. Association for Computational Linguistics, 1991. http://dx.doi.org/10.3115/981344.981374.
Full text
4
Morris, Jane, and Graeme Hirst. "Non-classical lexical semantic relations." In the HLT-NAACL Workshop. Association for Computational Linguistics, 2004. http://dx.doi.org/10.3115/1596431.1596438.
Full text
5
Hindle, Donald, and Mats Rooth. "Structural ambiguity and lexical relations." In the workshop. Association for Computational Linguistics, 1990. http://dx.doi.org/10.3115/116580.116664.
Full text
6
Séaghdha, Diarmuid Ó., and Ann Copestake. "Using lexical and relational similarity to classify semantic relations." In the 12th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 2009. http://dx.doi.org/10.3115/1609067.1609136.
Full text
7
Viegas, Evelyne, Stephen Beale, and Sergei Nirenburg. "The computational lexical semantics of syntagmatic relations." In the 36th annual meeting. Association for Computational Linguistics, 1998. http://dx.doi.org/10.3115/980691.980785.
Full text
8
Viegas, Evelyne, Stephen Beale, and Sergei Nirenburg. "The computational lexical semantics of syntagmatic relations." In the 17th international conference. Association for Computational Linguistics, 1998. http://dx.doi.org/10.3115/980432.980785.
Full text
9
Roemmele, Melissa. "Identifying Sensible Lexical Relations in Generated Stories." In Proceedings of the First Workshop on Narrative Understanding. Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/w19-2406.
Full text
10
Ramakrishnan, Ganesh, Apurva Jadhav, Ashutosh Joshi, Soumen Chakrabarti, and Pushpak Bhattacharyya. "Question Answering via Bayesian inference on lexical relations." In the ACL 2003 workshop. Association for Computational Linguistics, 2003. http://dx.doi.org/10.3115/1119312.1119313.
Full text