Large - Scale Automatic Extraction of anEnglish - Chinese Translation

We report experimental results on automatic extraction of an English-Chinese translation lexicon, by statistical analysis of a large parallel corpus, using limited amounts of linguistic knowledge. To our knowledge, these are the rst empirical results of the kind between an Indo-Europeanand non-Indo-Europeanlanguage for any signiicantvocabulary and corpus size. The learned vocabulary size is about 6,500 English words, achieving translation precision in the 86{96% range, with alignment proceeding at paragraph, sentence, and word levels. Speciically, we report (1) progress on the HKUST English-Chinese Parallel Bilingual Corpus, (2) experiments supportingthe usefulnessof restrictedlexical cues for statisticalparagraphand sentence alignment, and (3) experiments that question the role of hand-derived monolingual lexicons for automatic word translation acquisition. Using a hand-derived monolingual lexicon, the learned translation lexicon averages 2.33 Chinese translations per English entry, with a manually-ltered precision of 95.1%, and an automatically-ltered weighted precision of 86.0%. We then introduce a fully automatic two-stage statistical methodology that is able to learn translations for collocations. A statistically-learned monolingual Chinese lexicon is rst used to segment the Chinese text, before applying bilingual training to produce 6,429 English entries with 2.25 Chinese translations per entry. This method improves the manually-ltered precision to 96.0% and the automatically-ltered weighted precision to 91.0%, an error rate reduction of 35.7% from using a hand-derived monolingual lexicon.