ИСТИНА

Synonyms are one of two or more words or expressions of the same language that have the same or nearly the same meaning in some senses. Despite its importance in various Natural Language. Processing (NLP) applications, the task of synonym extraction remains challenging without satisfactory results in the NLP community. Thesauri are obviously the most common sources for synonyms. While such hand-crafted resources usually guarantee high quality of synonymy among entries, the amount of human effort involved in building a thesaurus, fixed domain coverage, and limited availability are the drawbacks of their use, indicating the necessity for automated processes for synonym extraction. Automatic determination of synonyms and/or semantically related words has various applications in Natural Language Processing. In this paper, we propose a novel method to identify synonyms from definition texts in a Nepal-English machine-readable dictionary (The Comparative and Etymological Dictionary of the Nepali Language (1931) by R.L Turner) - a monumental work in Nepali lexicography. The bilingual dictionary based method is based on the observation that found in the dictionary translations of the same word are usually synonyms, but the dictionary-based method has very low recall due to the limited coverage of bilingual dictionaries used. We cope with this problem attracting the monolingual (English) dictionary of synonyms. Extracted synonyms are evaluated in intrinsic experiment with another bilingual dictionary. Evaluation results show that our approach achieves satisfactory performance.