OWNS: Cross-lingual Word Sense Disambiguation Using Weighted Overlap Counts and Wordnet Based Similarity Measures

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 138–141, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics OWNS: Cross-lingual Word Sense Disambiguation Using Weighted Overlap Counts and Wordnet Based Similarity Measures Lipta Mahapatra Meera Mohan Dharmsinh Desai University Nadiad, India lipta.mahapatra89@gmail.com mu.mohan@gmail.com Mitesh M. Khapra Pushpak Bhattacharyya Indian Institute of Technology Bombay Powai, Mumbai 400076,India miteshk@cse.iitb.ac.in pb@cse.iitb.ac.in Abstract We report here our work on English French Cross-lingual Word Sense Disam- biguation where the task is to find the best French translation for a target English word depending on the context in which it is used. Our approach relies on identifying the nearest neighbors of the test sentence from the training data using a pairwise similarity measure. The proposed mea- sure finds the affinity between two sen- tences by calculating a weighted sum of the word overlap and the semantic over- lap between them. The semantic overlap is calculated using standard Wordnet Sim- ilarity measures. Once the nearest neigh- bors have been identified, the best trans- lation is found by taking a majority vote over the French translations of the nearest neighbors. 1 Introduction Cross Language Word Sense Disambiguation (CL-WSD) is the problem of finding the correct target language translation of a word given the context in which it appears in the source language. In many cases a full disambiguation may not be necessary as it is common for different meanings of a word to have the same translation. This is es- pecially true in cases where the sense distinction is very fine and two or more senses of a word are closely related. For example, the two senses of the word letter, namely, “formal document’ and “written/printed message” have the same French translation “lettre”. The problem is thus reduced to distinguishing between the coarser senses of a word and ignoring the finer sense distinctions which is known to be a common cause of errors in conventional WSD. CL-WSD can thus be seen as a slightly relaxed version of the conventional WSD problem. However, CL-WSD has its own set of challenges as described below. The translations learnt from a parallel corpus may contain a lot of errors. Such errors are hard to avoid due to the inherent noise associated with statistical alignment models. This problem can be overcome if good bilingual dictionaries are avail- able between the source and target language. Eu- roWordNet1 can be used to construct such a bilin- gual dictionary between English and French but it is not freely available. Instead, in this work, we use a noisy statistical dictionary learnt from the Europarl parallel corpus (Koehn, 2005) which is freely downloadable. Another challenge arises in the form of match- ing the lexical choice of a native speaker. For ex- ample, the word coach (as in, vehicle) may get translated differently as autocar, autobus or bus even when it appears in very similar contexts. Such decisions depend on the native speaker’s in- tuition and are very difficult for a machine to repli- …

Content truncated to 500 words