Unsupervised translated word sense disambiguation in constructing bilingual lexical database

Abstract

The performance of a machine translation system depends on the availability of bilingual lexical dictionary and completion of its word sense disambiguation performance. Word sense disambiguation plays a vital role in several applications such as machine translation, information retrieval and many other Natural Language Processing (NLP). In oder to construct a reliable machine translation system, not only consistent lexical database like WordNet (WN), but also word sense distinguished database, and bilingual lexical machine readable dictionary (MRD) are required to achieve an accurate translation. Since WN is for the English language, there have been several approcaches building WN like database for other languages, also known as multilingual WN, by linking and extending bilingual MRDs with synsets from WN. Lexical database like WN for Myanmar languae have been proposed in recent years which are bilingual lexical databases as the synsets from WN are merged with bilingual MRD. However, there are few limitations in constructing bilingual database based on MRD where thesauries are derived from WN yet there are no directed alignemnt of meanings between English and Myanmar language. In order to design a complete lexical database with correct parallel meanings for both languages, our proposed method composes a model which accurately matches the similar meanings between English words and Myanmar words by translating and comparing the word senses for both languages. The experimental result shows that the meanings for both languages are aligned as accurate as the manual alignment of the word senses for lexical database.