Tree-State Based Rule Selection Models for Hierarchical Phrase-Based Machine Translation
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2817-2822.
Abstract
Hierarchical phrase-based translation systems (HPBs) perform translation using a synchronous context free grammar which has only one unified non-terminal for every translation rule. While the usage of the unified non-terminal brings freedom to generate translations with almost arbitrary structures, it also takes the risks of generating low-quality translations which has a wrong syntactic structure. In this paper, we propose tree-state models to discriminate the good or bad usage of translation rules based on the syntactic structures of the source sentence. We propose to use statistical models and context dependent features to estimate the probability of each tree state for each translation rule and punish the usage of rules in the translation system which violates their tree states. Experimental results demonstrate that these simple models could bring significant improvements to the translation quality.
@inproceedings{ijcai2016p400,
title = {Tree-State Based Rule Selection Models for Hierarchical Phrase-Based Machine Translation},
author = {Huang, Shujian and Sun, Huifeng and Zhao, Chengqi and Su, Jinsong and Dai, Xin-Yu and Chen, Jiajun},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {2817--2822},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/400},
}
TY - CPAPER TI - Tree-State Based Rule Selection Models for Hierarchical Phrase-Based Machine Translation AU - Huang, Shujian AU - Sun, Huifeng AU - Zhao, Chengqi AU - Su, Jinsong AU - Dai, Xin-Yu AU - Chen, Jiajun T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 2817 EP - 2822 UR - https://ijcai.org/proceedings/2016/400 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: