Automatic Extraction of Low Frequency Bilingual Word Pairs from Parallel Corpora with Various Languages

In this paper, we propose a new learning method for extraction of low-frequency bilingual word pairs from parallel corpora with various languages. It is important to extract low-frequency bilingual word pairs because the frequencies of many bilingual word pairs are very low when large-scale parallel corpora are unobtainable. We use the following inference to extract low frequency bilingual word pairs: the word equivalents that adjoin the source language words of bilingual word pairs also adjoin the target language words of bilingual word pairs in local parts of bilingual sentence pairs. Evaluation experiments indicated that the extraction rate of our system was more than 8.0 percentage points higher than the extraction rate of the system based on the Dice coefficient. Moreover, the extraction rates of bilingual word pairs for which the frequencies are one and two respectively improved 11.0 and 6.6 percentage points using AIL.