Improving machine translation performance by exploiting non-parallel corpora

Munteanu, DS

doi:10.1162/089120105775299168

Improving machine translation performance by exploiting non-parallel corpora

2005-12-01

179

OA

AI

DOI：10.1162/089120105775299168

原文链接

查看原文

摘要

En 中文

We present a novel method for discovering parallel sentences in comparable, non-parallel corpora. We train a maximum entropy classifier that, given a pair of sentences, can reliably determine whether or not they are translations of each other. Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. We evaluate the quality of the extracted data by showing that it improves the performance of a state-of-the-art statistical machine translation system. We also show that a good-quality MT system can be built from scratch by starting with a very small parallel corpus (100,000 words) and exploiting a large non-parallel corpus. Thus, our method can be applied with great benefit to language pairs for which only scarce resources are available.

Improving machine translation performance by exploiting non-parallel corpora

摘要

AI总结

期刊

机构

引用论文