帮助 关于我们

返回检索结果

基于深度强化学习的维吾尔语人称代词指代消解
Anaphora Resolution of Uyghur Personal Pronouns Based on Deep Reinforcement Learning

查看参考文献19篇

文摘 针对深度神经网络模型仅学习当前指代链语义信息忽略了单个指代链识别结果的长期影响问题,提出一种结合深度强化学习(deep reinforcement learning)的维吾尔语人称代词指代消解方法.该方法将指代消解任务定义为强化学习环境下顺序决策过程,有效利用之前状态中先行语信息判定当前指代链指代关系.同时,采用基于整体奖励信号优化策略,相比于使用损失函数启发式优化特定的单个决策,该方法直接优化整体评估指标更加高效.最后在维吾尔语数据集进行实验,实验结果显示,该方法在维吾尔语人称代词指代消解任务中的F值为85.80%.实验结果表明,深度强化学习模型能显著提升维吾尔语人称代词指代消解性能.
其他语种文摘 Deep neural network models for Uyghur personal pronouns resolution learn semantic information for current anaphora chain,but ignore the long-term effects of single anaphora chain recognition results.This paper proposes a Uyghur personal pronoun anaphora resolution based on deep reinforcement learning.This method defines the anaphora resolution task as the sequential decision process under the reinforcement learning environment,and effectively uses the antecedent information in the previous state to determine the current personal pronoun-candidate antecedent pairs.In this study,we use an overall reward signal optimization strategy,which is more efficient than directly using the loss function heuristic to optimize a specific single decision.Finally,we conduct experiments in the Uyghur dataset.The experimental results show that the F value of this method in the Uyghur personal pronouns resolution task is 85.80%.The experimental results show that the deep reinforcement learning model can significantly improve the performance of the Uyghur personal pronouns resolution.
来源 电子学报 ,2020,48(6):1077-1083 【核心库】
DOI 10.3969/j.issn.0372-2112.2020.06.005
关键词 强化学习 ; 指代消解 ; 维吾尔语 ; 词向量 ; 深度学习 ; 自然语言处理
地址

1. 新疆大学信息科学与工程学院, 新疆, 乌鲁木齐, 830046  

2. 新疆大学网络中心, 新疆, 乌鲁木齐, 830046  

3. 新疆大学软件学院, 新疆, 乌鲁木齐, 83046

语种 中文
文献类型 研究性论文
ISSN 0372-2112
学科 自动化技术、计算机技术
基金 国家自然科学基金 ;  国家自然科学基金重点项目 ;  新疆自治区科技人才培养项目
文献收藏号 CSCD:6770166

参考文献 共 19 共1页

1.  Zhang R. Neural coreference resolution with deep biaffine attention by joint mention detection and mention clustering. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics,2018:102-107 CSCD被引 1 次    
2.  Chen C. Chinese zero pronoun resolution with deep neural networks. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics,2016:778-788 CSCD被引 2 次    
3.  Iida R. Intra-sentential subject zero anaphora resolution using multi-column convolutional neural network. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing,2016:1244-1254 CSCD被引 2 次    
4.  Niton B. Deep neural networks for coreference resolution for polish. Proceedings of the Eleventh International Conference on Language Resources and Evaluation,2018 CSCD被引 1 次    
5.  Plu J. Sanaphor++:combining deep neural networks with semantics for coreference resolution. Proceedings of the Eleventh International Conference on Language Resources and Evaluation,2018 CSCD被引 1 次    
6.  Haponchyk I. A practical perspective on latent structured prediction for coreference resolution. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics,2017:143-149 CSCD被引 1 次    
7.  Li J. Deep reinforcement learning for dialogue generation. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing,2016:1192-1202 CSCD被引 5 次    
8.  Zhao D. Deep reinforcement learning with visual attention for vehicle classification. IEEE Transactions on Cognitive and Developmental Systems,2017,9(4):356-367 CSCD被引 10 次    
9.  Zhang X. Sentence simplification with deep reinforcement learning. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing,2017:584-594 CSCD被引 2 次    
10.  Soon W M. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics,2001,27(4):521-544 CSCD被引 53 次    
11.  Lee K. End-to-end neural coreference resolution. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing,2017:188-197 CSCD被引 7 次    
12.  Clark K. Deep reinforcement learning for mention-ranking coreference models. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing,2016:2256-2262 CSCD被引 4 次    
13.  李冬白. 基于深度学习的维吾尔语人称代词指代消解. 中文信息学报,2017,31(4):80-88 CSCD被引 5 次    
14.  田生伟. 基于Bi-LSTM的维吾尔语人称代词指代消解. 电子学报,2018,46(7):1691-1699 CSCD被引 2 次    
15.  李敏. 基于深度学习的维吾尔语名词短语指代消解. 自动化学报,2017,43(11):1984-1992 CSCD被引 6 次    
16.  Pennington J. Glove:global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing,2014:1532-1543 CSCD被引 228 次    
17.  Xiong W. DeepPath:A reinforcement learning method for knowledge graph reasoning. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing,2017:564-573 CSCD被引 8 次    
18.  Duchi J. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research,2011,12(Jul):2121-2159 CSCD被引 176 次    
19.  Hinton G E. Improving Neural Networks by Preventing Co-adaptation of Feature Detectors. arXiv:1207.0580,2012 CSCD被引 55 次    
引证文献 2 篇

1 饶宁 基于多智能体深度强化学习的分布式协同干扰功率分配算法 电子学报,2022,50(6):1319-1330
CSCD被引 5 次

2 叶泽雨 基于深度强化学习的卫星电源冗余电池均衡控制策略 电子学报,2023,51(9):2419-2427
CSCD被引 0 次

显示所有2篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号