基于深度强化学习的维吾尔语人称代词指代消解

doi:10.3969/j.issn.0372-2112.2020.06.005

电子学报 ›› 2020, Vol. 48 ›› Issue (6): 1077-1083.DOI: 10.3969/j.issn.0372-2112.2020.06.005

所属专题：自然语言处理技术

基于深度强化学习的维吾尔语人称代词指代消解

杨启萌¹, 禹龙², 田生伟³, 艾山·吾买尔¹

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

收稿日期:2019-07-08 修回日期:2019-09-06 出版日期:2020-06-25
- 通讯作者:
- 禹龙
- 作者简介:
- 杨启萌 男,1993年9月出生,新疆昌吉人. 现为新疆大学博士研究生,主要研究领域为自然语言处理. E-mail:yqm_xju@163.com
  田生伟 男,1973年10月出生,新疆乌鲁木齐人.教授、博士生导师.主要研究领域为自然语言处理、图像处理. E-mail:tianshengwei@163.com
- 基金资助:
- 国家自然科学基金 (No.61563051，No.61662074，No.61262064）; 国家自然科学基金重点项目 (No.61331011）; 新疆自治区科技人才培养项目 (No.QN2016YX0051）

Anaphora Resolution of Uyghur Personal Pronouns Based on Deep Reinforcement Learning

YANG Qi-meng¹, YU Long², TIAN Sheng-wei³, Aishan Wumaier¹

1. School of Information Science and Engineering, Xinjiang University, Urumqi, Xinjiang 830046, China;
2. Network Center, Xinjiang University, Urumqi, Xinjiang 830046, China;
3. Software College, Xinjiang University, Urumqi, Xinjiang 830046, China

Received:2019-07-08 Revised:2019-09-06 Online:2020-06-25 Published:2020-06-25

摘要/Abstract

摘要： 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.

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

Abstract: 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.

Key words: reinforcement learning, anaphora resolution, Uyghur, word embedding, deep learning, natural language processing

中图分类号:

TP391

杨启萌, 禹龙, 田生伟, 艾山·吾买尔. 基于深度强化学习的维吾尔语人称代词指代消解[J]. 电子学报, 2020, 48(6): 1077-1083.

YANG Qi-meng, YU Long, TIAN Sheng-wei, Aishan Wumaier. Anaphora Resolution of Uyghur Personal Pronouns Based on Deep Reinforcement Learning[J]. Acta Electronica Sinica, 2020, 48(6): 1077-1083.

参考文献

[1] Zhang R,dos Santos C N,Yasunaga M,et al.Neural coreference resolution with deep biaffine attention by joint mention detection and mention clustering[A].Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics[C].Melbourne:ACL,2018.102-107.
[2] Chen C,Ng V.Chinese zero pronoun resolution with deep neural networks[A].Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics[C].Berlin:ACL,2016.778-788.
[3] Iida R,Torisawa K,Oh J H,et al.Intra-sentential subject zero anaphora resolution using multi-column convolutional neural network[A].Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing[C].Texas:EMNLP,2016.1244-1254.
[4] Nitoń B,Morawiecki P,Ogrodniczuk M.Deep neural networks for coreference resolution for polish[A].Proceedings of the Eleventh International Conference on Language Resources and Evaluation[C].Miyazaki:LREC,2018.
[5] Plu J,Prokofyev R,Tonon A,et al.Sanaphor++:combining deep neural networks with semantics for coreference resolution[A].Proceedings of the Eleventh International Conference on Language Resources and Evaluation[C].Miyazaki:LREC,2018.
[6] Haponchyk I,Moschitti A.A practical perspective on latent structured prediction for coreference resolution[A].Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics[C].Valencia:EACL,2017.143-149.
[7] Li J,Monroe W,Ritter A,et al.Deep reinforcement learning for dialogue generation[A].Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing[C].Austin:EMNLP,2016.1192-1202.
[8] Zhao D,Chen Y,Lv L.Deep reinforcement learning with visual attention for vehicle classification[J].IEEE Transactions on Cognitive and Developmental Systems,2017,9(4):356-367.
[9] Zhang X,Lapata M.Sentence simplification with deep reinforcement learning[A].Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing[C].Copenhagen:EMNLP,2017.584-594.
[10] Soon W M,Ng H T,Lim D C Y.A machine learning approach to coreference resolution of noun phrases[J].Computational Linguistics,2001,27(4):521-544.
[11] Lee K,He L,Lewis M,et al.End-to-end neural coreference resolution[A].Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing[C].Copenhagen:EMNLP,2017.188-197.
[12] Clark K,Manning C D.Deep reinforcement learning for mention-ranking coreference models[A].Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing[C].Austin:EMNLP,2016.2256-2262.
[13] 李冬白,田生伟,禹龙,等.基于深度学习的维吾尔语人称代词指代消解[J].中文信息学报,2017,31(4):80-88. LI Dong-bai,TIAN Sheng-wei,YU Long.Deep learning for pronominal anaphora resolution in Uyghur[J].Journal of Chinese Information Processing,2017,31(4):80-88.(in Chinese)
[14] 田生伟,秦越,禹龙,吐尔根·依布拉音,冯冠军.基于Bi-LSTM的维吾尔语人称代词指代消解[J].电子学报,2018,46(07):1691-1699. TIAN Sheng-wei,QIN Yue,et al.Anaphora resolution of Uyghur personal pronouns based on bi-lstm[J].Acta Electronica Sinica,2018,46(07):1691-1699.(in Chinese)
[15] 李敏,禹龙,田生伟,吐尔根·依布拉音,赵建国.基于深度学习的维吾尔语名词短语指代消解[J].自动化学报,2017,43(11):1984-1992. LI Min,YU Long,et al.Coreference resolution of Uyghur noun phrases based on deep learning[J].Acta Automatica Sinica,2017,43(11):1984-1992.(in Chinese)
[16] Pennington J,Socher R,Manning C.Glove:global vectors for word representation[A].Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing[C].Doha:EMNLP,2014.1532-1543.
[17] Xiong W,Hoang T,Wang W Y.DeepPath:A reinforcement learning method for knowledge graph reasoning[A].Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing[C].Copenhagen:EMNLP,2017.564-573.
[18] Duchi J,Hazan E,Singer Y.Adaptive subgradient methods for online learning and stochastic optimization[J].Journal of Machine Learning Research,2011,12(Jul):2121-2159.
[19] Hinton G E,Srivastava N,Krizhevsky A,et al.Improving Neural Networks by Preventing Co-adaptation of Feature Detectors[DB/OL].arXiv preprint arXiv:1207.0580,2012. >

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[2]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.
[3]	琚长瑞, 秦晓燕, 袁广林, 李豪, 朱虹. 尺度敏感损失与特征融合的快速小目标检测方法[J]. 电子学报, 2022, 50(9): 2119-2126.
[4]	张志昌, 于沛霖, 庞雅丽, 朱林, 曾扬扬. SMGN：用于对话状态跟踪的状态记忆图网络[J]. 电子学报, 2022, 50(8): 1851-1858.
[5]	张亚洲, 俞洋, 朱少林, 陈锐, 戎璐, 梁辉. 一种量子概率启发的对话讽刺识别网络模型[J]. 电子学报, 2022, 50(8): 1885-1893.
[6]	王飞扬, 冀鹏欣, 孙笠, 危倩, 李根, 张忠宝. 一种基于深度学习的动态社交网络用户对齐方法[J]. 电子学报, 2022, 50(8): 1925-1936.
[7]	徐兴荣, 刘聪, 李婷, 郭娜, 任崇广, 曾庆田. 基于双向准循环神经网络和注意力机制的业务流程剩余时间预测方法[J]. 电子学报, 2022, 50(8): 1975-1984.
[8]	欧阳与点, 谢鲲, 谢高岗, 文吉刚. 面向大规模网络测量的数据恢复算法：基于关联学习的张量填充[J]. 电子学报, 2022, 50(7): 1653-1663.
[9]	裴炤, 邱文涛, 王淼, 马苗, 张艳宁. 基于Transformer动态场景信息生成对抗网络的行人轨迹预测方法[J]. 电子学报, 2022, 50(7): 1537-1547.
[10]	段世红, 何昊, 徐诚, 殷楠, 王然. 未知环境下基于深度序列蒙特卡罗树搜索的信源导航方法[J]. 电子学报, 2022, 50(7): 1744-1752.
[11]	彭闯, 王伦文, 胡炜林. 融合深度特征的电磁频谱异常检测算法[J]. 电子学报, 2022, 50(6): 1359-1369.
[12]	饶宁, 许华, 蒋磊, 宋佰霖, 史蕴豪. 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[J]. 电子学报, 2022, 50(6): 1319-1330.
[13]	杨伟超, 杜宇, 文伟, 侯舒维, 徐常志, 张建华. 基于多重分形谱智能分析的卫星信号调制识别研究[J]. 电子学报, 2022, 50(6): 1336-1343.
[14]	宋佰霖, 许华, 齐子森, 饶宁, 彭翔. 一种基于深度强化学习的协同通信干扰决策算法[J]. 电子学报, 2022, 50(6): 1301-1309.
[15]	李政伟, 李佳树, 尤著宏, 聂茹, 赵欢, 钟堂波. 基于异质图注意力网络的miRNA与疾病关联预测算法[J]. 电子学报, 2022, 50(6): 1428-1435.