CELI: An Experiment with Cross Language Textual Entailment
26229Authors
nan
Abstract
This paper presents CELI’s participation in the SemEval Cross-lingual Textual Entailment for Content Synchronization task. 1
Keywords
Full Content
First Joint Conference on Lexical and Computational Semantics (*SEM), pages 696–700, Montr´eal, Canada, June 7-8, 2012. c⃝2012 Association for Computational Linguistics CELI: An Experiment with Cross Language Textual Entailment Milen Kouylekov Celi S.R.L. via San Quintino 31 Torino, Italy kouylekov@celi.it Luca Dini Celi S.R.L. via San Quintino 31 Torino, Italy dini@celi.it Alessio Bosca Celi S.R.L. via San Quintino 31 Torino, Italy bosca@celi.it Marco Trevisan Celi S.R.L. via San Quintino 31 Torino, Italy trevisan@celi.it Abstract This paper presents CELI’s participation in the SemEval Cross-lingual Textual Entailment for Content Synchronization task. 1 Introduction The Cross-Lingual Textual Entailment task (CLTE) is a new task that addresses textual entailment (TE) (Bentivogli et. al., 2011), targeting the cross- lingual content synchronization scenario proposed in (Mehdad et. al., 2011) and (Negri et. al., 2011). The task has interesting application scenarios that can be investigated. Some of them are content syn- chronization and cross language query alignment. The task is defined by the organizers as follows: Given a pair of topically related text fragments (T1 and T2) in different languages, the CLTE task con- sists of automatically annotating it with one of the following entailment judgments: • Bidirectional: the two fragments entail each other (semantic equivalence) • Forward: unidirectional entailment from T1 to T2 • Backward: unidirectional entailment from T2 to T1 • No Entailment: 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. Example for Spanish English pairs: • bidirectional Mozart naci en la ciudad de Salzburgo Mozart was born in Salzburg. • forward Mozart naci en la ciudad de Salzburgo Mozart was born on the 27th January 1756 in Salzburg. • backward Mozart naci el 27 de enero de 1756 en Salzburgo Mozart was born in 1756 in the city of Salzburg • no entailment Mozart naci el 27 de enero de 1756 en Salzburgo Mozart was born to Leopold and Anna Maria Pertl Mozart. 2 Our Approach to CLTE In our participation in the 2012 SemEval Cross- lingual Textual Entailment for Content Synchroniza- tion task (Negri et. al., 2012) we have developed an approach based on cross-language text similarity. We have modified our cross-language query similar- ity system TLike to handle longer texts. Our approach is based on four main resources: • A system for Natural Language Processing able to perform for each relevant language basic tasks such as part of speech disambiguation, lemmatization and named entity recognition. • A set of word based bilingual translation mod- ules. 696 • A semantic component able to associate a se- mantic vectorial representation to words. • We use Wikipedia as multilingual corpus. NLP modules are described in (Bosca and Dini, 2008), and will be no further detailed here. Word-based translation modules are composed by a bilingual lexicon look-up component coupled with a vector based translation filter, such as the one de- scribed in (Curtoni and Dini, 2008). In the context of the present experiments, such …
Content truncated to 500 words
Labeled Text
This paper presents CELI’s participation in the SemEval Cross-lingual Textual Entailment for Content Synchronization task. 1
Publication Details
- Paper ID:
- 26229
- Year:
- 2012
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan