Using the Textual Content of the LMF-Normalized Dictionaries for Identifying and Linking the Syntactic Behaviors to the Meanings

Proceedings of Recent Advances in Natural Language Processing, pages 168–175, Hissar, Bulgaria, Sep 7–9 2015. Using the Textual Content of the LMF-Normalized Dictionaries for Identifying and Linking the Syntactic Behaviours to the Meanings Elleuch Imen Gargouri Bilel Ben Hamadou Abdelmajid MIRACL Laboratory MIRACL Laboratory MIRACL Laboratory B.P. 1088 B.P. 1088 B.P. 242 3018 Sfax, Tunisia 3018 Sfax, Tunisia 3021 Sakiet-Ezzit Sfax, Tunisia imen.elleuch @fsegs.rnu.tn bilel.gargouri @fsegs.rnu.tn abdelmajid.benhamadou @isimsf.rnu.tn Abstract In this paper we propose an approach for identifying syntactic behaviours related to lexical items and linking them to the meanings. This approach is based on the analysis of the textual content presented in LMF normalized dictionaries by means of Definition and Context classes. The main particularity of these contents is their large availability and their semantically control due to their attachment to the meanings, which promotes the effective links between the syntactic behaviours and the meaning. In order to test the performance of the proposed approach, we tested it on an available Arabic LMF normalized dictionary. The experiment treats 9,800 verbs and allows us to evaluate the identified syntactic behaviours as well as their links to the meanings. 1 Introduction A syntactic lexicon is essentially a linguistic resource describing the sub-categorization structure of lexical entries that specify the number and the type of arguments composing the syntactic behaviour. The creation of such a lexicon has been a very large and daunting task. Often, it is approved that the frontier of performance on NLP tasks is shaped entirely by the quality of the syntactic lexicon used. (Carroll and Fang, 2004) showed that the performance of syntactic parsers is improved by using an exhaustive and detailed large lexicon that contains the syntactic knowledge. In the same vein, (Jikoun and Rike, 2004; Surdeanu et al., 2011) argued that a syntactic lexicon represents the core component resource for information extraction, machine translation systems and word sense disambiguation. Due to their importance, several syntactic lexicons appeared for various languages. Regarding English, we can mention FrameNet (Baker et al., 2010), which is a lexical resource for English based on semantic frames and confirmed by attestations in corpus. It aims to document the syntactic and semantic combinatorial (or valence) for each lexical entry through manual annotation of representative lexicographical examples selected from corpus. VerbNet (Kipper et al., 2008) is another lexicon for the English language. It groups verbs sharing the same syntactic and semantic behaviours into classes based on the semantic classification of Levin (1993). Concerning the French language, we can mention TLFi (Trésor de la Langue Française Informatisé) (Evelyne and Anne-Cécile, 2005), which is a large-scale public resource where sub- categorization is extracted from the dictionary “Trésor de la Langue Française Informatisé”. This dictionary, although very structured, was conceived for human use. The lexicon-grammar (Gross, 1975) is another syntactic lexicon for French. It contains information on the syntax of verbs, nouns, adjectives and adverbs into tables. As regards the Arabic language, we can cite the Arabic VerbNet (Mousser, 2010), which is a syntactic lexicon classifying Arabic …

Content truncated to 500 words