Multi-Attention-Based Capsule Network for Uyghur Personal Pronouns Resolution

Multi-Attention-Based Capsule Network for Uyghur Personal Pronouns Resolution
复制标题

基于多注意力的维吾尔族人称代词解析胶囊网络

DOI:
10.1109/access.2020.2989665
复制
发表时间:
2020
期刊:
影响因子:
3.9
通讯作者:
Song Jinmiao
Song Jinmiao
中科院分区:
计算机科学3区
文献类型:
--
作者:
Yang Qimeng;Yu Long;Tian Shengwei;Song Jinmiao

文献摘要

参考文献

相似文献

由于维吾尔语复杂的语言结构和有限的语料库,维吾尔语的回指消解是一项具有挑战性的任务。提出了一种基于多注意力的胶囊网络模型用于维吾尔语人称代词的自动识别,该模型能够有效地获取多层次、隐含的语义信息。该模型采用独立递归神经网络(IndRNN)实现长距离互依赖特征的提取。此外,胶囊网络可以提取更丰富的文本信息,以提高表达能力。与结合长短期记忆(LSTM)的单一注意力模型相比,基于多注意力的胶囊网络能够在不使用任何外部解析结果的情况下,通过多注意力机制捕获多层语义信息。在维吾尔语数据集上的实验结果表明,该方法优于现有的模型,获得了最高的F值83.85%。实验结果表明,该方法能有效地提高维吾尔语人称代词的识别性能。
Anaphora resolution of Uyghur is a challenging task because of complex language structure and limited corpus. We propose a multi-attention based capsule network model for Uyghur personal pronouns resolution, which can obtain the multi-layer and implicit semantic information effectively. Independently recurrent neural network (IndRNN) is applied in this model to achieve the interdependent features with long distance. Moreover, the capsule network can extract richer textual information to improve expression ability. Compared with the single attention-based model which combines Long Short-Term Memory (LSTM), the multi-attention based capsule network can capture multi-layer semantic information through a multi-attention mechanism without using any external parsing results. Experimental results on Uyghur dataset show that our approach surpasses the state-of-the-art models and gets the highest F-score of 83.85%. Meanwhile, our experimental results demonstrate the proposed method can effectively improve the performance of Uyghur personal pronouns resolution.
DOI: 10.18653/v1/p18-1053
发表时间: 2018-06
期刊: --
影响因子: --
作者:
Qingyu Yin;Yu Zhang;Weinan Zhang;Ting Liu;William Yang Wang
通讯作者: Qingyu Yin;Yu Zhang;Weinan Zhang;Ting Liu;William Yang Wang
DOI: --
发表时间: 2018-05
期刊: --
影响因子: --
作者:
J. Plu;Roman Prokofyev;Alberto Tonon;P. Cudré-Mauroux;D. Difallah;Raphael Troncy;Giuseppe Rizzo
通讯作者: J. Plu;Roman Prokofyev;Alberto Tonon;P. Cudré-Mauroux;D. Difallah;Raphael Troncy;Giuseppe Rizzo
DOI: 10.18653/v1/p19-1140
发表时间: 2019-07
期刊: --
影响因子: --
作者:
Yixin Cao;Zhiyuan Liu;Chengjiang Li;Zhiyuan Liu;Juan-Zi Li;Tat-Seng Chua
通讯作者: Yixin Cao;Zhiyuan Liu;Chengjiang Li;Zhiyuan Liu;Juan-Zi Li;Tat-Seng Chua
DOI: 10.3115/1073083.1073102
发表时间: 2002-07
期刊: --
影响因子: --
作者:
Vincent Ng;Claire Gardent
通讯作者: Vincent Ng;Claire Gardent
DOI: --
发表时间: 2011-06
期刊: --
影响因子: --
作者:
Dingcheng Li;Timothy Miller;William Schuler
通讯作者: Dingcheng Li;Timothy Miller;William Schuler