Supervised Attention for Sequence-to-Sequence Constituency Parsing
Supervised Attention for Sequence-to-Sequence Constituency Parsing
复制标题
DOI：
--
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Hidetaka Kamigaito;K. Hayashi;T. Hirao;Hiroya Takamura;M. Okumura;M. Nagata
中科院分区：
文献类型：
--
作者：
Hidetaka Kamigaito;K. Hayashi;T. Hirao;Hiroya Takamura;M. Okumura;M. Nagata
序列到序列(Seq2Seq)模型已成功地应用于机器翻译(MT)。最近，通过将监督注意引入到模型中，机器翻译的性能得到了改善。在本文中，我们将监督注意力引入到选区分析中，这可以被视为另一项翻译任务。在PTB语料库上的评价结果表明，在监督注意的作用下，括号F测量得到了改善。
The sequence-to-sequence (Seq2Seq) model has been successfully applied to machine translation (MT). Recently, MT performances were improved by incorporating supervised attention into the model. In this paper, we introduce supervised attention to constituency parsing that can be regarded as another translation task. Evaluation results on the PTB corpus showed that the bracketing F-measure was improved by supervised attention.