Semi-supervised lexicon mining from parenthetical expressions in monolingual web pages
Xianchao Wu, Naoaki Okazaki, Jun’ichi Tsujii · 2009
This paper presents a semi-supervised learning framework for mining Chinese-English lexicons from large amount of Chinese Web pages. The issue is motivated by the observation that many Chinese neologisms are accompanied by their English translations in the form of parenthesis. We classify parenthetical translations into bilingual abbreviations, transliterations, and translations. A frequency-based term recognition approach is applied for extracting bilingual abbreviations. A self-training algorithm is proposed for mining transliteration and translation lexicons. In which, we employ available lexicons in terms of morpheme levels, i.e., phoneme correspondences in transliteration and grapheme (e.g., suffix, stem, and prefix) correspondences in translation. The experimental results verified the effectiveness of our approaches.