关键词: 自动编码机, 过滤模型, 调序规则表, 机器翻译

Abstract: In statistical machine translation system, lexical reordering table and phrase-table are always huge. Tuning and filtering the phrase-table has been research focus long time, while few researchers focus on filtering the lexical reordering table. This paper treats filtering lexical reordering table as the problem of short text classification, proposes a filtering model of lexical reordering table based on Autoencoder. This model uses the Autoencoder to score the    reordering rules firstly, then filters the lexical reordering table by minimal difference strategy, finally recalculates lexical reordering score table used for machine translation decoding. The experimental results show that the size of lexical reordering table reduces 40% while the BLEU (bilingual evaluation understudy) increases 0.19 and 0.26 by using the proposed model on public English-Chinese corpus and Uyghur-Chinese corpus.

Key words: Autoencoder, filtering model, lexical reordering table, machine translation