TY - GEN
T1 - Phrase table training for precision and recall
T2 - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT
AU - Deng, Yonggang
AU - Xu, Jia
AU - Gao, Yuqing
PY - 2008
Y1 - 2008
N2 - In this work, the problem of extracting phrase translation is formulated as an information retrieval process implemented with a log-linear model aiming for a balanced precision and recall. We present a generic phrase training algorithm which is parameterized with feature functions and can be optimized jointly with the translation engine to directly maximize the end-to-end system performance. Multiple data-driven feature functions are proposed to capture the quality and confidence of phrases and phrase pairs. Experimental results demonstrate consistent and significant improvement over the widely used method that is based on word alignment matrix only.
AB - In this work, the problem of extracting phrase translation is formulated as an information retrieval process implemented with a log-linear model aiming for a balanced precision and recall. We present a generic phrase training algorithm which is parameterized with feature functions and can be optimized jointly with the translation engine to directly maximize the end-to-end system performance. Multiple data-driven feature functions are proposed to capture the quality and confidence of phrases and phrase pairs. Experimental results demonstrate consistent and significant improvement over the widely used method that is based on word alignment matrix only.
UR - http://www.scopus.com/inward/record.url?scp=70349879247&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70349879247&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:70349879247
SN - 9781932432046
T3 - ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
SP - 81
EP - 88
BT - ACL-08
Y2 - 15 June 2008 through 20 June 2008
ER -