UBA: Using Automatic Translation and Wikipedia for Cross-Lingual Lexical Substitution

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 242–247, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics UBA: Using Automatic Translation and Wikipedia for Cross-Lingual Lexical Substitution Pierpaolo Basile Dept. of Computer Science University of Bari “Aldo Moro” Via E. Orabona, 4 70125 Bari (ITALY) basilepp@di.uniba.it Giovanni Semeraro Dept. of Computer Science University of Bari “Aldo Moro” Via E. Orabona, 4 70125 Bari (ITALY) semeraro@di.uniba.it Abstract This paper presents the participation of the University of Bari (UBA) at the SemEval- 2010 Cross-Lingual Lexical Substitution Task. The goal of the task is to substi- tute a word in a language Ls, which oc- curs in a particular context, by provid- ing the best synonyms in a different lan- guage Lt which fit in that context. This task has a strict relation with the task of automatic machine translation, but there are some differences: Cross-lingual lexi- cal substitution targets one word at a time and the main goal is to find as many good translations as possible for the given tar- get word. Moreover, there are some con- nections with Word Sense Disambiguation (WSD) algorithms. Indeed, understand- ing the meaning of the target word is nec- essary to find the best substitutions. An important aspect of this kind of task is the possibility of finding synonyms with- out using a particular sense inventory or a specific parallel corpus, thus allowing the participation of unsupervised approaches. UBA proposes two systems: the former is based on an automatic translation system which exploits Google Translator, the lat- ter is based on a parallel corpus approach which relies on Wikipedia in order to find the best substitutions. 1 Introduction The goal of the Cross-Lingual Lexical Substitu- tion (CLLS) task is to substitute a word in a lan- guage Ls, which occurs in a particular context, by providing the best substitutions in a different language Lt. In SemEval-2010 the source lan- guage Ls is English, while the target language Lt is Spanish. Clearly, this task is related to Lexical Substitution (LS) (McCarthy and Navigli, 2007) which consists in selecting an alternative word for a given one in a particular context by preserving its meaning. The main difference between the LS task and the CLLS one is that in LS source and target languages are the same. CLLS is not a easy task since neither a list of candidate words nor a specific parallel corpus are supplied by the orga- nizers. However, this opens the possibility of us- ing several knowledge sources, instead of a single one fixed by the task organizers. Therefore, the system must identify a set of candidate words in Lt and then select only those words which fit the context. From another point of view, the cross- lingual nature of the task allows to exploit auto- matic machine translation methods, hence the goal is to find as many good translations as possible for the given target word. A thorough description of the task can be found in (Mihalcea …

Content truncated to 500 words