arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.07282cs.CLcs.AI
收藏

基于AMR的语义神经机器翻译

Semantic Neural Machine Translation using AMR

University of Rochester(罗切斯特大学);Westlake University(西湖大学);IBM T.J. Watson Research Center(IBM托马斯·J·沃森研究中心);Xiamen University(厦门大学)

Linfeng Song, Daniel Gildea, Yue Zhang, Zhiguo Wang, Jinsong Su

摘要:

语义表示对于机器翻译是有用的,这是直观的,主要是因为它们可以帮助强制意义保持和处理机器翻译模型的数据稀疏性(许多句子对应于一个意义)。另一方面,利用语义进行神经机器翻译(NMT)的工作很少。在这项工作中,我们研究的有用性AMR(简称抽象意义表示)的NMT。在标准英语到德语数据集上的实验表明,将AMR作为额外的知识可以显着改善基于注意力的序列到序列神经翻译模型。

英文摘要:

It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (short for abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑