POS-tagger for English-Vietnamese bilingual corpus

Abstract

Corpus-based Natural Language Processing (NLP) tasks for such popular languages as English, French, etc. have been well studied with satisfactory achievements. In contrast, corpus-based NLP tasks for unpopular languages (e.g. Vietnamese) are at a deadlock due to absence of annotated training data for these languages. Furthermore, hand-annotation of even reasonably well-determined features such as part-of-speech (POS) tags has proved to be labor intensive and costly. In this paper, we suggest a solution to partially overcome the annotated resource shortage in Vietnamese by building a POS-tagger for an automatically word-aligned English-Vietnamese parallel Corpus (named EVC). This POS-tagger made use of the Transformation-Based Learning (or TBL) method to bootstrap the POS-annotation results of the English POS-tagger by exploiting the POS-information of the corresponding Vietnamese words via their word-alignments in EVC. Then, we directly project POS-annotations from English side to Vietnamese via available word alignments. This POS-annotated Vietnamese corpus will be manually corrected to become an annotated training data for Vietnamese NLP tasks such as POS-tagger, Phrase-Chunker, Parser, Word-Sense Disambiguator, etc.