No description available.

Made available in DSpace on 2016-06-02T20:25:06Z (GMT). No. of bitstreams: 1 3060.pdf: 1410899 bytes, checksum: 3015872a282e606335436041c1a0d0ff (MD5) Previous issue date: 2010-02-25 / Financiadora de Estudos e Projetos / Among the most important lexical semantic relations to the class of adjectives is antonymy, i. e., opposition of senses as in fat/thin . WordNet, a lexical database for English, both establishes semantic relationships (such as synonymy, hiperonymy, etc.) between words and presents the concept of indirect antonymy (via synonymy: obese=fat/thin) for adjectives. This type of antonymy has not been represented at WordNet.Br yet, the Brazilian Portuguese WordNet, and at Electronic Thesaurus for Brazilian Portuguese (TeP), which contains the WordNet.Br core synsets. Thus, this research aims to study the antonymy in adjectives of Brazilian Portuguese (BP), to contribute to the refinement of the TeP and of WordNet.Br s database. The study takes up the occurrences of the 100 most frequent adjectives in the Mac-Morpho corpus from the LacioWeb project, which contains newspaper articles of Folha de São Paulo of the year 1994 and has 1,167,183 tokens. The adjectives were extracted by the Unitex concordancer. The research is motivated by three questions ( when two adjectives have closely similar meanings, why do they not have the same antonym? ; if antonymy is so important, why do many descriptive adjectives seem to have no antonym? ; and how the direct antonymy can be established? ). The main objectives are: to establish a lexical network that relates direct antonymy between adjectives and indirect antonymy between the synonyms of each adjective and its antonyms and to implement them in TeP, refining the representation of antonymy. / Dentre as relações léxico-semânticas mais importantes para a classe dos adjetivos está a antonímia, ou seja, a oposição de sentidos, como em: gordo/magro . A WordNet, uma base de dados lexicais do inglês, que estabelece relações léxico-semânticas e semântico-conceituais (como sinonímia, hiperonímia, respectivamente, etc.) entre as palavras, apresenta também o conceito de antonímia indireta (via sinonímia: obeso=gordo/magro) para os adjetivos. Esse tipo de antonímia ainda não está representada na WordNet.Br (WN.Br), a base de dados para o português do Brasil, e no Thesaurus Eletrônico para o Português do Brasil (TeP), que contém os synsets básicos da WN.Br. Sendo assim, a presente pesquisa tem como objetivo estudar a antonímia nos adjetivos do Português do Brasil (PB), com vistas a uma contribuição para o refinamento do TeP e da base de dados da WN.Br. O estudo é feito tendo como base as ocorrências dos 100 adjetivos mais frequentes no corpus Mac-Morpho, do projeto LacioWeb, que contém artigos jornalísticos de dez cadernos da Folha de São Paulo de 1994 e é composto de 1.167.183 ocorrências. Os adjetivos foram extraídos pelo concordanciador Unitex. Tomam-se por base na pesquisa três perguntas ( por que dois adjetivos com significados similares não têm o mesmo antônimo? , se a antonímia é tão importante, por que muitos adjetivos parecem não ter antônimos? e como é estabelecida a antonímia direta? ). Visa-se, assim, estabelecer uma rede semântica que possa relacionar a antonímia direta entre adjetivos e a antonímia indireta existente entre os sinônimos de cada adjetivo e seus antônimos, buscando implementá-las no TeP, refinando aí a representação da antonímia.

This thesis performs an empirical analysis of Word2Vec by comparing its output to WordNet, a well-known, human-curated lexical database. It finds that Word2Vec tends to uncover more of certain types of semantic relations than others -- with Word2Vec returning more hypernyms, synonomyns and hyponyms than hyponyms or holonyms. It also shows the probability that neighbors separated by a given cosine distance in Word2Vec are semantically related in WordNet. This result both adds to our understanding of the still-unknown Word2Vec and helps to benchmark new semantic tools built from word vectors.

No description available.

No description available.

Made available in DSpace on 2015-04-14T13:37:41Z (GMT). No. of bitstreams: 1 410054.pdf: 1283010 bytes, checksum: 4163a4a808a0986e0178af14f442c4d0 (MD5) Previous issue date: 2009-01-22 / A meta principal desta tese ? a realiza??o de um estudo descritivo explanat?rio dos adjetivos predicativos descritivos voltados para o sujeito, tendo em vista a sua utilidade para o aperfei?oamento de sistemas computacionais que necessitam processar a linguagem natural. Primeiramente, retomam-se os estudos mais relevantes acerca dos adjetivos em geral com intuito de evidenciar que eles formam uma classe de palavras com comportamento sint?ticosem?ntico muito peculiar, em especial, em contextos de dupla predica??o. Para melhor compreender as quest?es implicadas nesses contextos, investe-se na descri??o das eventualidades denotadas pelo predicado prim?rio e pelo adjetivo predicativo descritivo por este ser um caminho que aponta a rela??o entre l?xico, sintaxe e sem?ntica. Buscam-se abordagens sem?nticas que tentam descrever n?o s? as propriedades de tais eventualidades, mas tamb?m a rela??o entre elas. Para representar a rela??o entre as eventualidades denotadas pelo predicado prim?rio e pelo adjetivo predicativo descritivo, baseia-se em abordagens que n?o visam apenas configurar os fen?menos da linguagem e sua resolu??o, mas tamb?m ? efici?ncia necess?ria ? sua inclus?o em aplica??es computacionais. Por fim, sugerem-se formas de incorporar os resultados ling??sticos obtidos nessa pesquisa em wordnets. Tal empreitada se mostra relevante tanto do ponto de vista da ling??stica, por testar o potencial de aplica??o das teorias adotadas nesta pesquisa, quanto do ponto de vista da computa??o, por contribuir no processo de enriquecimento desse tipo de l?xico, bem como no aperfei?oamento de sistemas de PLN

No description available.

In this thesis, we make automatic video categorization and summarization by using subtitles of videos. We propose two methods for video categorization. The first method makes unsupervised categorization by applying natural language processing techniques on video subtitles and uses the WordNet lexical database and WordNet domains. The method starts with text preprocessing. Then a keyword extraction algorithm and a word sense disambiguation method are applied. The WordNet domains that correspond to the correct senses of keywords are extracted. Video is assigned a category label based on the extracted domains. The second method has the same steps for extracting WordNet domains of video but makes categorization by using a learning module. Experiments with documentary videos give promising results in discovering the correct categories of videos. Video summarization algorithms present condensed versions of a full length video by identifying the most significant parts of the video. We propose a video summarization method using the subtitles of videos and text summarization techniques. We identify significant sentences in the subtitles of a video by using text summarization techniques and then we compose a video summary by finding the video parts corresponding to these summary sentences.

In this thesis, cross-lingual information retrieval (CLIR) approaches are comparatively evaluated for Turkish and English texts. As a complementary study, knowledge-based methods for word sense disambiguation (WSD), which is one of the most important parts of the CLIR studies, are compared for Turkish words. Query translation and sense indexing based CLIR approaches are used in this study. In query translation approach, we use automatic and manual word sense disambiguation methods and Google translation service during translation of queries. In sense indexing based approach, documents are indexed according to meanings of words instead of words themselves. Retrieval of documents is performed according to meanings of the query words as well. During the identification of intended meaning of query terms, manual and automatic word sense disambiguation methods are used and compared to each other. Knowledge based WSD methods that use different gloss enrichment techniques are compared for Turkish words. Turkish WordNet is used as a primary knowledge base and English WordNet and Turkish Wikipedia are employed as enrichment resources. Meanings of words are more clearly identified by using semantic relations defined in WordNets and Turkish Wikipedia. Also, during calculation of semantic relatedness of senses, cosine similarity metric is used as an alternative metric to word overlap count. Effects of using cosine similarity metric are observed for each WSD methods that use different knowledge bases.

<p>This study describes the English verb ’consider’ and the characteristics of some of its senses. An investigation of this kind may be useful, since a machine translation program, SYSTRAN, has invariably translated ’consider’ with the Swedish verbs ’betrakta’ (Eng: ’view’, regard’) and ’anse’ (Eng: ’regard’). This handling of ’consider’ is not satisfactory in all contexts.</p><p>Since ’consider’ is a cogitative verb, it is fascinating to observe that both the theory of semantic primes and universals and conceptual semantics are concerned with cogitation in various ways. Anna Wierzbicka, who is one of the advocates of semantic primes and universals, argues that THINK should be considered as a semantic prime. Moreover, one of the prime issues of conceptual semantics is to describe how thoughts are constructed by virtue of e.g. linguistic components, perception and experience.</p><p>In order to define and clarify the distinctions between the different senses, we have taken advantage of the theory of mental spaces.</p><p>This thesis has been structured in accordance with the meanings that have been indicated in WordNet as to ’consider’. As a consequence, the senses that ’consider’ represents have been organized to form the subsequent groups: ’Observation’, ’Opinion’ together with its sub-group ’Likelihood’ and ’Cogitation’ followed by its sub-group ’Attention/Consideration’.</p><p>A concordance tool, http://www.nla.se/culler, provided us with 90 literary quotations that were collected in a corpus. Afterwards, these citations were distributed between the groups mentioned above and translated into Swedish by SYSTRAN.</p><p>Furthermore, the meanings as to ’consider’ have also been related to the senses, recorded by the FrameNet scholars. Here, ’consider’ is regarded as a verb of ’Cogitation’ and ’Categorization’.</p><p>When this study was accomplished, it could be inferred that certain senses are connected to specific syntactic constructions. In other cases, however, the distinctions between various meanings can only be explained by virtue of semantics.</p><p>To conclude, it appears to be likely that an implementation is facilitated if a specific syntactic construction can be tied to a particular sense. This may be the case concerning some meanings of ’consider’. Machine translation is presumably a much more laborious task, if one is solely governed by semantic conditions.</p>