• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 5
  • 1
  • 1
  • 1
  • Tagged with
  • 9
  • 9
  • 3
  • 3
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • 2
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Semantic spaces for video analysis of behaviour

Xu, Xun January 2016 (has links)
There are ever growing interests from the computer vision community into human behaviour analysis based on visual sensors. These interests generally include: (1) behaviour recognition - given a video clip or specific spatio-temporal volume of interest discriminate it into one or more of a set of pre-defined categories; (2) behaviour retrieval - given a video or textual description as query, search for video clips with related behaviour; (3) behaviour summarisation - given a number of video clips, summarise out representative and distinct behaviours. Although countless efforts have been dedicated into problems mentioned above, few works have attempted to analyse human behaviours in a semantic space. In this thesis, we define semantic spaces as a collection of high-dimensional Euclidean space in which semantic meaningful events, e.g. individual word, phrase and visual event, can be represented as vectors or distributions which are referred to as semantic representations. With the semantic space, semantic texts, visual events can be quantitatively compared by inner product, distance and divergence. The introduction of semantic spaces can bring lots of benefits for visual analysis. For example, discovering semantic representations for visual data can facilitate semantic meaningful video summarisation, retrieval and anomaly detection. Semantic space can also seamlessly bridge categories and datasets which are conventionally treated independent. This has encouraged the sharing of data and knowledge across categories and even datasets to improve recognition performance and reduce labelling effort. Moreover, semantic space has the ability to generalise learned model beyond known classes which is usually referred to as zero-shot learning. Nevertheless, discovering such a semantic space is non-trivial due to (1) semantic space is hard to define manually. Humans always have a good sense of specifying the semantic relatedness between visual and textual instances. But a measurable and finite semantic space can be difficult to construct with limited manual supervision. As a result, constructing semantic space from data is adopted to learn in an unsupervised manner; (2) It is hard to build a universal semantic space, i.e. this space is always contextual dependent. So it is important to build semantic space upon selected data such that it is always meaningful within the context. Even with a well constructed semantic space, challenges are still present including; (3) how to represent visual instances in the semantic space; and (4) how to mitigate the misalignment of visual feature and semantic spaces across categories and even datasets when knowledge/data are generalised. This thesis tackles the above challenges by exploiting data from different sources and building contextual semantic space with which data and knowledge can be transferred and shared to facilitate the general video behaviour analysis. To demonstrate the efficacy of semantic space for behaviour analysis, we focus on studying real world problems including surveillance behaviour analysis, zero-shot human action recognition and zero-shot crowd behaviour recognition with techniques specifically tailored for the nature of each problem. Firstly, for video surveillances scenes, we propose to discover semantic representations from the visual data in an unsupervised manner. This is due to the largely availability of unlabelled visual data in surveillance systems. By representing visual instances in the semantic space, data and annotations can be generalised to new events and even new surveillance scenes. Specifically, to detect abnormal events this thesis studies a geometrical alignment between semantic representation of events across scenes. Semantic actions can be thus transferred to new scenes and abnormal events can be detected in an unsupervised way. To model multiple surveillance scenes simultaneously, we show how to learn a shared semantic representation across a group of semantic related scenes through a multi-layer clustering of scenes. With multi-scene modelling we show how to improve surveillance tasks including scene activity profiling/understanding, crossscene query-by-example, behaviour classification, and video summarisation. Secondly, to avoid extremely costly and ambiguous video annotating, we investigate how to generalise recognition models learned from known categories to novel ones, which is often termed as zero-shot learning. To exploit the limited human supervision, e.g. category names, we construct the semantic space via a word-vector representation trained on large textual corpus in an unsupervised manner. Representation of visual instance in semantic space is obtained by learning a visual-to-semantic mapping. We notice that blindly applying the mapping learned from known categories to novel categories can cause bias and deteriorating the performance which is termed as domain shift. To solve this problem we employed techniques including semisupervised learning, self-training, hubness correction, multi-task learning and domain adaptation. All these methods in combine achieve state-of-the-art performance in zero-shot human action task. In the last, we study the possibility to re-use known and manually labelled semantic crowd attributes to recognise rare and unknown crowd behaviours. This task is termed as zero-shot crowd behaviours recognition. Crucially we point out that given the multi-labelled nature of semantic crowd attributes, zero-shot recognition can be improved by exploiting the co-occurrence between attributes. To summarise, this thesis studies methods for analysing video behaviours and demonstrates that exploring semantic spaces for video analysis is advantageous and more importantly enables multi-scene analysis and zero-shot learning beyond conventional learning strategies.
2

The Best Balance : An Investigation of Expressions Describing Taste Experiences

Hurtig, Alexander January 2005 (has links)
<p>Taste, or gustation, has long been considered a primitive, and even non-rational, perceptual sense. Taste, as a subject of academic research, has been given very little attention; especially, when contrasted to other human perceptual senses. The knowledge of how people express and discuss their perceptions and sensations of tastes, and, specifically, the descriptions of tastes of chocolate, is very limited.</p><p>Furthermore, the terminological inconsistency in the vocabulary of chocolate tasting, with the risk of misunderstanding or miscommunication, suggests that a basic method for representing tastes is needed.</p><p>This thesis presents a study of how people actually express the perception or sensation of tasting, and specifically when tasting chocolate. This study also explores the possibility of crafting a method for use when describing the tastes of chocolate.</p><p>The study was carried out by holding two tasting workshops. The first one was concerned with recording conversations about tasting chocolate. Participants were asked to taste different kinds of chocolates and, freely, discuss what they perceived and sensed. In the second workshop the participants were asked to describe the tastes of chocolate using predetermined vocabulary and formatted questionnaires.</p><p>The results of this study are linguistic semantic analyses of the different words that were used, and also a proposal for a prototypical method to use when tasting chocolate.</p>
3

The Best Balance : An Investigation of Expressions Describing Taste Experiences

Hurtig, Alexander January 2005 (has links)
Taste, or gustation, has long been considered a primitive, and even non-rational, perceptual sense. Taste, as a subject of academic research, has been given very little attention; especially, when contrasted to other human perceptual senses. The knowledge of how people express and discuss their perceptions and sensations of tastes, and, specifically, the descriptions of tastes of chocolate, is very limited. Furthermore, the terminological inconsistency in the vocabulary of chocolate tasting, with the risk of misunderstanding or miscommunication, suggests that a basic method for representing tastes is needed. This thesis presents a study of how people actually express the perception or sensation of tasting, and specifically when tasting chocolate. This study also explores the possibility of crafting a method for use when describing the tastes of chocolate. The study was carried out by holding two tasting workshops. The first one was concerned with recording conversations about tasting chocolate. Participants were asked to taste different kinds of chocolates and, freely, discuss what they perceived and sensed. In the second workshop the participants were asked to describe the tastes of chocolate using predetermined vocabulary and formatted questionnaires. The results of this study are linguistic semantic analyses of the different words that were used, and also a proposal for a prototypical method to use when tasting chocolate.
4

Ensembles of Semantic Spaces : On Combining Models of Distributional Semantics with Applications in Healthcare

Henriksson, Aron January 2015 (has links)
Distributional semantics allows models of linguistic meaning to be derived from observations of language use in large amounts of text. By modeling the meaning of words in semantic (vector) space on the basis of co-occurrence information, distributional semantics permits a quantitative interpretation of (relative) word meaning in an unsupervised setting, i.e., human annotations are not required. The ability to obtain inexpensive word representations in this manner helps to alleviate the bottleneck of fully supervised approaches to natural language processing, especially since models of distributional semantics are data-driven and hence agnostic to both language and domain. All that is required to obtain distributed word representations is a sizeable corpus; however, the composition of the semantic space is not only affected by the underlying data but also by certain model hyperparameters. While these can be optimized for a specific downstream task, there are currently limitations to the extent the many aspects of semantics can be captured in a single model. This dissertation investigates the possibility of capturing multiple aspects of lexical semantics by adopting the ensemble methodology within a distributional semantic framework to create ensembles of semantic spaces. To that end, various strategies for creating the constituent semantic spaces, as well as for combining them, are explored in a number of studies. The notion of semantic space ensembles is generalizable across languages and domains; however, the use of unsupervised methods is particularly valuable in low-resource settings, in particular when annotated corpora are scarce, as in the domain of Swedish healthcare. The semantic space ensembles are here empirically evaluated for tasks that have promising applications in healthcare. It is shown that semantic space ensembles – created by exploiting various corpora and data types, as well as by adjusting model hyperparameters such as the size of the context window and the strategy for handling word order within the context window – are able to outperform the use of any single constituent model on a range of tasks. The semantic space ensembles are used both directly for k-nearest neighbors retrieval and for semi-supervised machine learning. Applying semantic space ensembles to important medical problems facilitates the secondary use of healthcare data, which, despite its abundance and transformative potential, is grossly underutilized. / <p>At the time of the doctoral defense, the following papers were unpublished and had a status as follows: Paper 4 and 5: Unpublished conference papers.</p> / High-Performance Data Mining for Drug Effect Detection
5

Semantic annotation of music collections: A computational approach

Sordo, Mohamed 27 February 2012 (has links)
El consum de la música ha canviat dràsticament en els últims anys. Amb l’arribada de la música digital, el cost de producció s’ha reduït considerablement. L’expansió de la Web ha ajudat a promoure l’exploració de molt més contingut musical. Algunes botigues musicals on-line, com iTunes o Amazon, posseeixen milions de cançons a les seves col.leccions. No obstant, accedir a aquestes col.leccions d’una manera eficient és encara un gran repte. En aquesta tesis ens centrem en el problema d’anotar col.leccions musicals amb paraules semàntiques, també conegudes com tags. Els mètodes utilitzats en aquesta tesi estan fonamentats sobre els camps de recuperació de la informació, l’inteligència artificial, i el procesament del senyal. Proposem un algorisme per anotar música automàticament, utilitzant similitud d’audio a nivell de contingut per propagar tags entre cançons. L’algorisme s’avalua extensament utilitzant múltiples col.leccions musicals de diferent mida i qualitat de les dades, incloent una col.lecció de més de mig milió de cançons, anotades amb tags socials derivats d’una comunitat musical. Avaluem la qualitat del nostre algorisme mitjançant una comparació amb algorismes de l’estat de l’art. Addicionalment, discutim la importància d’utilitzar mesures de avaluació que cobreixen diferents dimensions, és a dir, avaluacions a nivell de cançó i a nivell de tag. El nostre algorisme ha estat avaluat i s’ha classificat en altes posicions en el concurs d’avaluació internacional MIREX 2011. Els resultats obtinguts també demostren algunes limitacions de l’anotació automàtica, relacionades amb les inconsistències en les dades, la correlació de conceptes i la dificultat de capturar alguns tags personals amb informació del contingut. Això és més evident en les comunitats musicals, on els usuaris poden anotar cançons amb qualsevol paraula, sigui aquesta contextual o no. Per tal d’abordar aquestes limitacions, presentem un ampli estudi sobre la naturalesa de les folksonomies musicals. Concretament, estudiem si les anotacions fetes per una gran comunitat d’usuaris coincideixen amb un vocabulari més controlat i estructurat per part d’experts en el camp. Els resultats revelen que alguns tags estan clarament definits i compresos tant des del punt de vista dels experts com el de la saviesa popular, mentre que n’hi ha d’altres sobre els quals és difícil trobar un consens. Finalment, estenem el nostre previ treball a un ampli ventall de conceptes semàntics. Presentem un nou métode per a descobrir conceptes semàntics implícits en els tags socials, i classificar aquests tags pel que fa als conceptes semàntics. Les darreres troballes poden ajudar a entendre la naturalesa dels tags socials, i per tant ser beneficials per a una addicional millora de la anotació automàtica de la música. / Music consumption has changed drastically in the last few years. With the arrival of digital music, the cost of production has substantially dropped. The expansion of the World Wide Web has helped to promote the exploration of many more music content. Online stores, such as iTunes or Amazon, own music collections in the order of millions of songs. Accessing these large collections in an effective manner is still a big challenge. In this dissertation we focus on the problem of annotating music collections with semantic words, also called tags. The foundations of all the methods used in this dissertation are based on techniques from the fields of information retrieval, machine learning, and signal processing. We propose an automatic music annotation algorithm that uses content-based audio similarity to propagate tags among songs. The algorithm is evaluated extensively using multiple music collections of varying size and quality of the data, including a large music collection of more than a half million songs, annotated with social tags derived from a music community. We assess the quality of our proposed algorithm by comparing it with several state of the art approaches. We also discuss the importance of using evaluation measures that cover different dimensions; per– song and per–tag evaluation. Our proposal achieves state of the art results, and has ranked high in the MIREX 2011 evaluation campaign. The obtained results also show some limitations of automatic tagging, related to data inconsistencies, correlation of concepts and the difficulty to capture some personal tags with content information. This is more evident in music communites, where users can annotate songs with any free text word. In order to tackle these issues, we present an in-depth study of the nature of music folksonomies. We concretely study whether tag annotations made by a large community (i.e. a folksonomy) correspond with a more controlled, structured vocabulary by experts in the music and the psychology fields. Results reveal that some tags are clearly defined and understood both by the experts and the wisdom of crowds, while it is difficult to achieve a common consensus on the meaning of other tags. Finally, we extend our previous work to a wide range of semantic concepts. We present a novel way to uncover facets implicit in social tagging, and classify the tags with respect to these semantic facets. The latter findings can help to understand the nature of social tags, and thus be beneficial for further improvement of semantic tagging of music. Our findings have significant implications for music information retrieval systems that assist users to explore large music collections, digging for content they might like. / El consumo de la música ha cambiado drásticamente en los últimos años. Con la llegada de la música digital, el coste de producción se ha reducido considerablemente. La expansión de la Web ha ayudado a promover la exploración de mucho más contenido musical. Algunas tiendas musicales on-line, como iTunes o Amazon, poseen millones de canciones en sus colecciones. Sin embargo, acceder a estas colecciones de una manera eficiente es todavía un gran reto. En esta tesis nos centramos en el problema de anotar colecciones musicales con palabras semánticas, también conocidas como tags. Los métodos utilizados en esta tesis están cimentados sobre los campos de recuperación de la información, la inteligencia artifical, y el procesamiento del señal. Proponemos un algoritmo para anotar música automáticamente, usando similitud de audio a nivel de contenido para propagar tags entre canciones. El algoritmo se evalúa extensamente usando múltiples colecciones musicales de distinto tamaño y calidad de los datos, incluyendo una colección de más de medio millón de canciones, anotadas con tags sociales derivados de una comunidad musical. Evaluamos la calidad de nuestro algoritmo mediante una comparación con algoritmos del estado del arte. Adicionalmente, discutimos la importancia de usar medidas de evaluación que cubren diferentes dimensiones; es decir, evaluaciones a nivel de canción y a nivel de tag. Nuestro algoritmo ha sido evaluado y se clasificado en altas posiciones en el concurso de evaluación internacional MIREX 2011. Los resultados obtenidos también demuestran algunas limitaciones de la anotación automática, relacionadas con las inconsistencias en los datos, la correlación de conceptos y la dificultad de capturar algunos tags personales con información del contenido. Esto es más evidente en las comunidades musicales, donde los usuarios pueden anotar canciones con cualquier palabra, sea esta contextual o no. Con el fin de abordar estas limitaciones, presentamos un amplio estudio sobre la naturaleza de las folksonomías musicales. Concretamente, estudiamos si las anotaciones hechas por una gran comunidad de usuarios concuerdan con un vocabulario más controlado y estructurado por parte de expertos en el campo. Los resultados revelan que algunos tags están claramente definidos y comprendidos tanto desde el punto de vista de los expertos como el de la sabiduría popular, mientras que hay otros tags sobre los cuales es difícil encontrar un consenso. Por último, extendemos nuestro previo trabajo a un amplio abanico de conceptos semánticos. Presentamos un método novedoso para descubrir conceptos semánticos implícitos en los tags sociales, y clasificar dichos tags con respecto a los conceptos semánticos. Los últimos hallazgos pueden ayudar a entender la naturaleza de los tags sociales, y por consiguiente ser beneficiales para una adicional mejora para la anotación automática de la música.
6

Analýza struktury a formálních prostředků jakutského eposu oloncho na příkladu oloncha "Er soghotox" / Analysis of the structure and formal means of the Yakut epic olonkho, on the example of the oloncho "Er soghotox"

Vlasák, Jonáš January 2016 (has links)
The topic of the thesis is interpretation of a yakutian epic (olonkho) Modun Er Soghotox through the concept of J. Lotman's classifying boundaries. In the begining, the thesis is trying to put the olonkho into broader genre context of yakutian folklore. Formal aspect of the text is important for the definition of the genre, therefore the work attempts to describe some of the most common distinctive features, especially alliteration and paralelism. The second part tries to analyze the worlds of olonkho as the Lotman's semantic spaces. Each world keeps significantly different semantic environment. Crossing the boundaries between these spaces initiates the plot of olonkho. The last part is trying to understand the role of the hero in olonkho, mainly as the mediator between the semantic spaces.
7

Semantic Spaces of Clinical Text : Leveraging Distributional Semantics for Natural Language Processing of Electronic Health Records

Henriksson, Aron January 2013 (has links)
The large amounts of clinical data generated by electronic health record systems are an underutilized resource, which, if tapped, has enormous potential to improve health care. Since the majority of this data is in the form of unstructured text, which is challenging to analyze computationally, there is a need for sophisticated clinical language processing methods. Unsupervised methods that exploit statistical properties of the data are particularly valuable due to the limited availability of annotated corpora in the clinical domain. Information extraction and natural language processing systems need to incorporate some knowledge of semantics. One approach exploits the distributional properties of language – more specifically, term co-occurrence information – to model the relative meaning of terms in high-dimensional vector space. Such methods have been used with success in a number of general language processing tasks; however, their application in the clinical domain has previously only been explored to a limited extent. By applying models of distributional semantics to clinical text, semantic spaces can be constructed in a completely unsupervised fashion. Semantic spaces of clinical text can then be utilized in a number of medically relevant applications. The application of distributional semantics in the clinical domain is here demonstrated in three use cases: (1) synonym extraction of medical terms, (2) assignment of diagnosis codes and (3) identification of adverse drug reactions. To apply distributional semantics effectively to a wide range of both general and, in particular, clinical language processing tasks, certain limitations or challenges need to be addressed, such as how to model the meaning of multiword terms and account for the function of negation: a simple means of incorporating paraphrasing and negation in a distributional semantic framework is here proposed and evaluated. The notion of ensembles of semantic spaces is also introduced; these are shown to outperform the use of a single semantic space on the synonym extraction task. This idea allows different models of distributional semantics, with different parameter configurations and induced from different corpora, to be combined. This is not least important in the clinical domain, as it allows potentially limited amounts of clinical data to be supplemented with data from other, more readily available sources. The importance of configuring the dimensionality of semantic spaces, particularly when – as is typically the case in the clinical domain – the vocabulary grows large, is also demonstrated. / De stora mängder kliniska data som genereras i patientjournalsystem är en underutnyttjad resurs med en enorm potential att förbättra hälso- och sjukvården. Då merparten av kliniska data är i form av ostrukturerad text, vilken är utmanande för datorer att analysera, finns det ett behov av sofistikerade metoder som kan behandla kliniskt språk. Metoder som inte kräver märkta exempel utan istället utnyttjar statistiska egenskaper i datamängden är särskilt värdefulla, med tanke på den begränsade tillgången till annoterade korpusar i den kliniska domänen. System för informationsextraktion och språkbehandling behöver innehålla viss kunskap om semantik. En metod går ut på att utnyttja de distributionella egenskaperna hos språk – mer specifikt, statistisk över hur termer samförekommer – för att modellera den relativa betydelsen av termer i ett högdimensionellt vektorrum. Metoden har använts med framgång i en rad uppgifter för behandling av allmänna språk; dess tillämpning i den kliniska domänen har dock endast utforskats i mindre utsträckning. Genom att tillämpa modeller för distributionell semantik på klinisk text kan semantiska rum konstrueras utan någon tillgång till märkta exempel. Semantiska rum av klinisk text kan sedan användas i en rad medicinskt relevanta tillämpningar. Tillämpningen av distributionell semantik i den kliniska domänen illustreras här i tre användningsområden: (1) synonymextraktion av medicinska termer, (2) tilldelning av diagnoskoder och (3) identifiering av läkemedelsbiverkningar. Det krävs dock att vissa begränsningar eller utmaningar adresseras för att möjliggöra en effektiv tillämpning av distributionell semantik på ett brett spektrum av uppgifter som behandlar språk – både allmänt och, i synnerhet, kliniskt – såsom hur man kan modellera betydelsen av flerordstermer och redogöra för funktionen av negation: ett enkelt sätt att modellera parafrasering och negation i ett distributionellt semantiskt ramverk presenteras och utvärderas. Idén om ensembler av semantisk rum introduceras också; dessa överträffer användningen av ett enda semantiskt rum för synonymextraktion. Den här metoden möjliggör en kombination av olika modeller för distributionell semantik, med olika parameterkonfigurationer samt inducerade från olika korpusar. Detta är inte minst viktigt i den kliniska domänen, då det gör det möjligt att komplettera potentiellt begränsade mängder kliniska data med data från andra, mer lättillgängliga källor. Arbetet påvisar också vikten av att konfigurera dimensionaliteten av semantiska rum, i synnerhet när vokabulären är omfattande, vilket är vanligt i den kliniska domänen. / High-Performance Data Mining for Drug Effect Detection (DADEL)
8

Психосемантическое исследование воли у студентов : магистерская диссертация / Psychosemantic study of the will of students

Киселева, Д. О., Kiseleva, D. O. January 2018 (has links)
The object of the study was volitional sphere of personality. The subject of the study was the semantic fields of the concept of "will." The master's thesis consists of an introduction, three chapters, conclusion, a list of literature (70 sources) and applications, including forms of applied techniques, the classifier of associative connections, and the scheme of volitional action. The volume of the master's thesis is 103 pages, on which are placed 8 figures and 13 tables. The introduction reveals the relevance of the research problem, the development of the problem, the purpose and objectives of the research, the object and subject of the research, the main hypothesis are formulated, the methods and the empirical base are specified. The first and second chapters include a review of foreign and domestic literature on the topic of the study. The first and second chapters include a review of foreign and domestic literature on the topic of the study. The first chapter includes a description of approaches to the study of will and methods of its investigation. The second chapter includes a description of the psychosemantic approach in psychology in general and the study of the will in particular. Conclusions on the first and second chapters are the results of the study of theoretical material. The third Chapter is devoted to the empirical part of the study. It describes the organization and methods studies and the results obtained for all methodologies used: Ch. Osgood semantic differential, associative experiment. The conclusions of Chapter 3 include the main results of the empirical study. In conclusion, the results of the theoretical and empirical parts of the work, as well as conclusions on the hypotheses put forward, the practical significance of the study. / Объектом исследования является волевая сфера личности. Предметом исследования стали смысловые поля понятия «воля». Магистерская диссертация состоит из введения, трех глав, заключения, списка литературы (70 источников) и приложений, включающих в себя бланки применявшихся методик, классификатор ассоциативных связей и схему волевого действия. Объем магистерской диссертации 103 страницы, на которых размещены 8 рисунков и 13 таблиц. Во введении раскрывается актуальность проблемы исследования, разработанность проблематики, ставятся цель и задачи исследования, определяются объект и предмет исследования, формулируется основная гипотеза, указываются методы и эмпирическая база. Первая и вторая главы включают в себя обзор иностранной и отечественной литературы по теме исследования. Первая глава включает в себя описание подходов к изучению воли и методов ее исследования. Вторая глава включает в себя описание психосемантического подхода в психологии в целом и к изучению воли в частности. Выводы по первой и второй главам представляют собой итоги по изучению теоретического материала. Третья глава посвящена эмпирической части исследования. В ней представлено описание организации и методов проведенного исследования и результатов, полученных по всем использованным методам: семантический дифференциал Ч. Осгуда и ассоциативный эксперимент. Выводы по главе 3 включают в себя основные результаты эмпирического исследования. В заключении в обобщенном виде изложены результаты теоретической и эмпирической частей работы, а также выводы по выдвинутым гипотезам, обоснована практическая значимость исследования.
9

La géométrie du sens : la polysémie verbale en question / The geometry of meaning : verbal polysemy in question

Sendi, Monia 18 December 2015 (has links)
Notre étude porte sur la notion de géométrie de sens. Ainsi, l’étude de la notion de verbe occupe l’axe principal de notre thèse. Cette notion est connue par sa complexité. Cela s’explique par la forte polysémie des verbes français. Nous avons focalisé notre étude sur l’analyse syntactico-sémantique des verbes « monter» et « passer ». La notion de polysémie, malgré sa grande importance, reste toujours très difficile à formaliser. Nous avons tenté, dans cette étude, d’utiliser trois dictionnaires électroniques pour désambiguïser les verbes « monter » et « passer ». Ce travail permet de rendre compte de l’influence de la syntaxe et du lexique sur les sens de ces deux verbes. Dans notre démarche, nous avons utilisé la méthode de désambiguïsation automatique de B. Victorri qui a pour spécificité l’analyse des unités lexicales polysémiques. Ce modèle se base sur des théories linguistiques et il exploite les mathématiques et l’informatique dans l’objectif de bien décrire et de résoudre le problème de la polysémie verbale. Donc, notre travail est pluridisciplinaire. C’est là où l’informatique et les mathématiques sont au service de l’analyse des langues naturelles. / Our study focuses on the concept of geometry of sense. the study of the concept of verb occupies the main axis of our thesis. This concept is known for its complexity. This is explained by the polysemy of French verbs. We focused our study on the syntactic-semantic analysis of the two verbs "to climb " and "to pass". Indeed, the multiplicity of use involves the notion of verbal polysemy. This notion despite its importance is still very difficult to formulate. We have tried in this study using three electronic dictionaries to disambiguate the verbs "to climb " and "to pass". This work allows us to account for the influence of the syntax and vocabulary of the senses of these two verbs. We explained the opportunity to disambiguate a polysemous verb not by recourse to a list of synonyms but by a set of meanings in specific syntactic constructions. In our approach, we used an automatic method of disambiguation B Victorri that has specificity for the analysis of polysemous lexical units. We found that there is reconciliation between the theoretical analysis and the analysis given by this method. This model is based on linguistic theories and operates mathematics and computer with the aim to clearly describe and solve the problem of verbal polysemy. So our work is multidisciplinary. This is where computer science and mathematics is at the service of the analysis of natural languages.

Page generated in 1.5908 seconds