Neural recovery machine for Chinese dropped pronoun
Neural recovery machine for Chinese dropped pronoun
复制标题
DOI：
10.1007/s11704-018-7136-7
复制
发表时间：
2016-05
影响因子：
4.2
通讯作者：
Weinan Zhang;Ting Liu;Qingyu Yin;Yu Zhang
中科院分区：
文献类型：
--
作者：
Weinan Zhang;Ting Liu;Qingyu Yin;Yu Zhang
脱落代词在汉语、日语等脱落语言中普遍存在，以往的研究主要集中在脱落代词恢复的经验特征上。在本文中，我们提出了一个神经恢复机（NRM）的模型和恢复在中国的DP，以避免非平凡的特征工程过程。实验结果表明，所提出的NRM显着优于国家的最先进的方法在两个异构数据集。进一步的汉语零代词消解实验结果表明，通过将零代词还原为零代词，可以提高零代词消解的性能。
Dropped pronouns (DPs) are ubiquitous in prodrop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine (NRM) to model and recover DPs in Chinese to avoid the non-trivial feature engineering process. The experimental results show that the proposed NRM significantly outperforms the state-of-the-art approaches on two heterogeneous datasets. Further experimental results of Chinese zero pronoun (ZP) resolution show that the performance of ZP resolution can also be improved by recovering the ZPs to DPs.