Kata Gabor

Institut National des Langues et Civilisations Orientales | INALCO

An important trend in recent works on lexical semantics has been the development of learning methods capable of extracting semantic information from text corpora. The majority of these methods are based on the distributional hypothesis of meaning and acquire semantic information by identifying distributional patterns in texts. In this article, we p...

Our paper reports an attempt to apply an unsupervised clustering algorithm to a Hungarian treebank in order to obtain semantic verb classes. Starting from the hypothesis that semantic metapredicates underlie verbs' syntactic realization, we investigate how one can obtain semantically motivated verb classes by automatic means. The 150 most frequent...

We present in this paper a method to automatically acquire a syntactic lexicon of subcategorization frames for French verbs directly from large corpora. The method is evaluated against existing lexical resources: we show that our system is capable of producing new frames that were not previously registered. Lastly, we show that it is possible to in...

This paper deals with the extraction of semantic relations from scientific texts. Pattern-based representations are compared to word embeddings in unsupervised clustering experiments, according to their potential to discover new types of semantic relations and recognize their instances. The results indicate that sequential pattern mining can signif...

We propose a method for improving access to scientific literature by analyzing the content of research papers beyond citation links and topic tracking. Our model relies on a typology of explicit semantic relations. These relations are instantiated in the abstract/introduction part of the papers and can be identified automatically using textual data...

Cikkünkben a lexikális behelyettesítési feladat (lexical substitution) magyarra adatptálását és két különböző megoldásának tesztelését tárgyaljuk. A lexikális behelyettesítés célja olyan algoritmus megalkotása, mely képes egy lexikális egység egy-egy mondatbeli előfordulását másik egységgel helyettesíteni olyan módon, hogy a mondat eredeti jelentés...

Cet article traite de l'acquisition automatique de schémas de sous-catégorisation de verbes en français et de classification automatique de verbes.

Nous décrivons dans cet article une méthode permettant l'acquisition d'un lexique syn-taxique des verbes du français à partir de l'analyse automatique de gros corpus. Nous évaluons cette méthode par rapport à des ressources existantes et nous montrons que notre système pro-duit automatiquement de nouvelles données qui peuvent compléter les lexiques...

A significant number of natural language processing applications cannot work without syntactic parsing. The automatic syntactic analysis of natural language texts in turn requires an efficient method for differentiating between elements that belong to the predicate's argument structure and those that are attached to it as adjuncts. The focus of our...

Our applied linguistic research aims at increasing the efficiency of a rule-based information extraction (IE) system by enhancing it with further grammatical knowledge. The input of the IE system is made up of sentences of business news. The event of the piece of news is identified through the main verb of the sentence, while parti cipants and circ...