String-to-dependency statistical machine translation
Computational Linguistics（2010）
摘要
We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model. Experiments show that the algorithm achieves significant improvement in MT performance over a state-of-the-art hierarchical string-to-string system on NIST MT06 and MT08 newswire evaluation sets.
更多查看译文
关键词
traditional n-gram language model,statistical machine translation,long distance word relation,mt performance,nist mt06,mt08 newswire evaluation set,string-to-dependency statistical machine translation,state-of-the-art hierarchical string-to-string system,significant improvement,novel string-to-dependency algorithm,target dependency language model,language model
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要