Word-sense disambiguation for machine translation

Abstract

In word sense disambiguation, a system attempts to determine the sense of a word from contextual features. Major barriers to building a high-performing word sense disambiguation system include the difficulty of labeling data for this task and of predicting fine-grained sense distinctions. These issues stem partly from the fact that the task is being treated in isolation from possible uses of automatically disambiguated data. In this paper, we consider the related task of word translation, where we wish to determine the correct translation of a word from context. We can use parallel language corpora as a large supply of partially labeled data for this task. We present algorithms for solving the word translation problem and demonstrate a significant improvement over a baseline system. We then show that the word-translation system can be used to improve performance on a simplified machinetranslation task and can effectively and accurately prune the set of candidate translations for a word.

Target-Side Context for Discriminative Models in Statistical Machine Translation

“…For sense disambiguation, source context is the main source of information, as has been shown in previous work (Vickrey et al, 2005), (Carpuat and Wu, 2007), (Gimpel and Smith, 2008) inter alia. Consider the first set of examples in Figure 1, produced by a strong baseline PBMT system.…”

A Sense-Based Translation Model for Statistical Machine Translation

“…WSD for SMT As we mentioned in Section 1, WSD has been successfully reformulated and adapted to SMT (Vickrey et al, 2005;Carpuat and Wu, 2007;Chan et al, 2007). Rather than predicting word senses for ambiguous words, the reformulated WSD directly predicts target translations for source words with context information.…”

“…In contrast to the standard WSD formulation, Vickrey et al (2005) reformulate the task of WSD for SMT as predicting possible target translations rather than senses for ambiguous source words. They show that such a reformulated WSD can improve the accuracy of a simplified word translation task.…”

n-Best Reranking for the Efficient Integration of Word Sense Disambiguation and Statistical Machine Translation

“…Vickrey et al [19] experimented with a disambiguation task for French-English translation, with the choices defined as the set of words aligned to the ambiguous word, as given by GIZA++ [11]. A logistic regression classifier with collocational and bag-of-words features is used to predict the translations.…”