LIMSI: Translations as Source of Indirect Supervision for Multilingual All-Words Sense Disambiguation and Entity Linking

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 298–302, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics LIMSI: Translations as Source of Indirect Supervision for Multilingual All-Words Sense Disambiguation and Entity Linking Marianna Apidianaki LIMSI-CNRS Rue John von Neumann 91405 Orsay Cedex, France marianna@limsi.fr Li Gong IMMI-CNRS Rue John von Neumann 91405 Orsay Cedex, France gong@limsi.fr Abstract We present the LIMSI submission to the Mul- tilingual Word Sense Disambiguation and En- tity Linking task of SemEval-2015. The sys- tem exploits the parallelism of the multilin- gual test data and uses translations as source of indirect supervision for sense selection. The LIMSI system gets best results in English in all domains and shows that alignment in- formation can successfully guide disambigua- tion. This simple but effective method can serve to generate high quality sense annotated data for WSD system training. 1 Introduction This paper describes the LIMSI system at the Multi- lingual Word Sense Disambiguation (WSD) and En- tity Linking (EL) task of SemEval-2015 (Moro and Navigli, 2015). The system performs sense selec- tion by combining translation information obtained through alignment of the multilingual test set with sense ranking. It can thus be described as semi- supervised given the indirect supervision provided by the translations. The alignment correspondences serve as constraints for reducing the search space for each word to BabelNet synsets (hereafter, Ba- belSynsets) containing the translation and the re- tained synsets are sorted according to the BabelNet sense ranking. Our goal is to test the contribution of translations in multilingual WSD with no recourse to context information. The system needs no train- ing and can be applied directly to parallel data. The evaluation results show that the LIMSI sys- tem outperforms all systems in all domains in En- glish and highlight the important role of translations in guiding disambiguation. This simple yet effective approach can serve to generate high quality sense annotations for WSD system training. In what fol- lows, we provide a detailed description of the sys- tem, an analysis of the results and a discussion of the factors that determine the efficiency of the method. 2 Task Description The SemEval-2015 Multilingual WSD and EL task (Moro and Navigli, 2015) aims to promote joint re- search in these two closely-related topics. WSD refers to the task of assigning meanings to occur- rences of words in texts (Navigli, 2009) and its multilingual counterpart involves the identification of semantically adequate translations (Resnik and Yarowsky, 1997; Ide et al., 2002; Apidianaki, 2009). EL, on the other side, aims at linking entities in a text to the most suitable entry in a knowledge base. The systems participating in the Multilingual WSD and EL task can make a choice between different options (WSD, EL or both) and one or several WSD settings (all-words or specific part-of-speech disam- biguation). Contrary to previous tasks (Navigli et al., 2013), the SemEval-2015 task addresses the dis- ambiguation of words of all content parts of speech. No training data is provided and …

Content truncated to 500 words