TY - GEN
T1 - Phrase table pruning via submodular function maximization
AU - Nishino, Masaaki
AU - Suzuki, Jun
AU - Nagata, Masaaki
N1 - Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016
Y1 - 2016
N2 - Phrase table pruning is the act of removing phrase pairs from a phrase table to make it smaller, ideally removing the least useful phrases first. We propose a phrase table pruning method that formulates the task as a submodular function maximization problem, and solves it by using a greedy heuristic algorithm. The proposed method can scale with input size and long phrases, and experiments show that it achieves higher BLEU scores than state-of-the-art pruning methods.
AB - Phrase table pruning is the act of removing phrase pairs from a phrase table to make it smaller, ideally removing the least useful phrases first. We propose a phrase table pruning method that formulates the task as a submodular function maximization problem, and solves it by using a greedy heuristic algorithm. The proposed method can scale with input size and long phrases, and experiments show that it achieves higher BLEU scores than state-of-the-art pruning methods.
UR - http://www.scopus.com/inward/record.url?scp=85016600335&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85016600335&partnerID=8YFLogxK
U2 - 10.18653/v1/p16-2066
DO - 10.18653/v1/p16-2066
M3 - Conference contribution
AN - SCOPUS:85016600335
T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
SP - 406
EP - 411
BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
PB - Association for Computational Linguistics (ACL)
T2 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Y2 - 7 August 2016 through 12 August 2016
ER -