BUAP: Lexical and Semantic Similarity for Cross-lingual Textual Entailment

First Joint Conference on Lexical and Computational Semantics (*SEM), pages 706–709, Montr´eal, Canada, June 7-8, 2012. c⃝2012 Association for Computational Linguistics BUAP: Lexical and Semantic Similarity for Cross-lingual Textual Entailment Darnes Vilari˜no, David Pinto, Mireya Tovar, Saul Le´on, Esteban Castillo Benem´erita Universidad Aut´onoma de Puebla, Faculty of Computer Science 14 Sur & Av. San Claudio, CU Puebla, Puebla, M´exico {darnes, dpinto, mtovar}@cs.buap.mx saul.ls@live.com, ecjbuap@gmail.com Abstract In this paper we present a report of the two di- fferent runs submitted to the task 8 of Semeval 2012 for the evaluation of Cross-lingual Tex- tual Entailment in the framework of Content Synchronization. Both approaches are based on textual similarity, and the entailment judg- ment (bidirectional, forward, backward or no entailment) is given based on a set of decision rules. The first approach uses textual simi- larity on the translated and original versions of the texts, whereas the second approach ex- pands the terms by means of synonyms. The evaluation of both approaches show a similar behavior which is still close to the average and median. 1 Introduction Cross-lingual Textual Entailment (CLTE) has been recently proposed by (Mehdad et al., 2010; Mehdad et al., 2011) as an extension of the Textual Entail- ment task (Dagan and Glickman, 2004). Given a text (T) and an hypothesis (H) in different languages, the CLTE task consists of determining if the mea- ning of H can be inferred from the meaning of T. In this paper we present a report of the obtained results after submitting two different runs for the Task 8 of Semeval 2012, named “Cross-lingual Tex- tual Entailment for Content Synchronization” (Negri et al., 2012). In this task, the Cross-Lingual Tex- tual Entailment addresses textual entailment recog- nition under a new dimension (cross-linguality), and within a new challenging application scenario (con- tent synchronization). The task 8 of Semeval 2012 may be formally defined as follows: Given a pair of topically related text fragments (T1 and T2) in different languages, the task consists of automatically annotating it with one of the follo- wing entailment judgments: • Bidirectional (T1 → T2 & T1 ← T2): the two fragments entail each other (semantic equiva- lence) • Forward (T1 → T2 & T1 ! ← T2): unidirec- tional entailment from T1 to T2 • Backward (T1 ! → T2 & T1 ← T2): unidirec- tional entailment from T2 to T1 • No Entailment (T1 ! → T2 & T1 ! ← T2): there is no entailment between T1 and T2 In this task, both T1 and T2 are assumed to be TRUE statements; hence in the dataset there are no contradictory pairs. Cross-lingual datasets are avai- lable for the following language combinations: • Spanish/English (SPA-ENG) • German/English (DEU-ENG) • Italian/English (ITA-ENG) • French/English (FRA-ENG) The remaining of this paper is structured as fo- llows: Section 2 describes the two different approa- ches presented in the competition. The obtained re- sults are shown and dicussed in Section 3. Finally, the findings of this work are given in Section 4. …

Content truncated to 500 words