Improving machine translation performance by exploiting non-parallel corpora

Improving machine translation performance by exploiting non-parallel corpora (2005)

by Dragos Stefan Munteanu , Daniel Marcu

Venue:	Computational Linguistics
Citations:	56 - 2 self

Datum	Value	Source
TITLE	Improving machine translation performance by exploiting non-parallel corpora	INFERENCE
AUTHOR NAME	Dragos Stefan Munteanu	SVM HeaderParse 0.2
AUTHOR AFFIL	Information Sciences Institute; University of Southern California	SVM HeaderParse 0.2
AUTHOR NAME	Daniel Marcu	SVM HeaderParse 0.2
AUTHOR AFFIL	Information Sciences Institute; University of Southern California	SVM HeaderParse 0.2
ABSTRACT	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. 1.	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	Computational Linguistics	INFERENCE
VENUE TYPE	JOURNAL	INFERENCE
PAGES	477--504	INFERENCE
VOLUME	31	INFERENCE
CITATIONS	38 found	ParsCit 1.0