基于Bi-LSTM的维吾尔语人称代词指代消解

doi:10.3969/j.issn.0372-2112.2018.07.022

电子学报 ›› 2018, Vol. 46 ›› Issue (7): 1691-1699.DOI: 10.3969/j.issn.0372-2112.2018.07.022

基于Bi-LSTM的维吾尔语人称代词指代消解

田生伟¹, 秦越², 禹龙³, 吐尔根·依布拉音², 冯冠军⁴

1. 新疆大学软件学院, 新疆乌鲁木齐 830008;
2. 新疆大学信息科学与工程学院, 新疆乌鲁木齐 830046;
3. 新疆大学网络中心, 新疆乌鲁木齐 830046;
4. 新疆大学人文学院, 新疆乌鲁木齐 830046

收稿日期:2017-03-30 修回日期:2017-09-09 出版日期:2018-07-25
- 通讯作者:
- 禹龙
- 作者简介:
- 田生伟,男,1973年出生,新疆乌鲁木齐人,博士,现为新疆大学教授,主要研究领域为计算机智能技术和自然语言处理.E-mail:tianshengwei@163.com;秦越,女,1992年出生,新疆昌吉人,现为新疆大学硕士研究生,主要研究领域为自然语言处理.E-mail:qinyue_xju@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）; 新疆维吾尔自治区科技人才培养项目 (No.QN2016YX0051）

Anaphora Resolution of Uyghur Personal Pronouns Based on Bi-LSTM

TIAN Sheng-wei¹, QIN Yue², YU Long³, Turgun Ibrahim², FENG Guan-jun⁴

1. College of Software, Xinjiang University, Urumqi, Xinjiang 830008, China;
2. College of Information Science and Technology, Xinjiang University, Urumqi, Xinjiang 830046;China;
3. Network Center, Xinjiang University, Urumqi, Xinjiang 830046, China;
4. College of Humanities, Xinjiang University, Urumqi, Xinjiang 830046, China

Received:2017-03-30 Revised:2017-09-09 Online:2018-07-25 Published:2018-07-25
- Corresponding author:
- YU Long
- Supported by:
- National Natural Science Foundation of China (No.61563051, No.61662074, No.61262064); Key Program of National Natural Science Foundation of China (No.61331011); Science and Technology Talents Cultivation Program of Xinjiang Uygur Autonomous Region (No.QN2016YX0051)

摘要/Abstract

摘要： 针对维吾尔语人称代词指代现象，提出利用双向长短时记忆网络（Bi-directional long short term memory，Bi-LSTM）的深度学习机制进行基于深层语义信息的维吾尔语人称代词指代消解.首先将富含语义和句法信息的word embedding向量作为Bi-LSTM的输入，挖掘维吾尔语隐含的上下文语义层面特征；其次对维吾尔语人称代词指代现象进行探索，提取针对人称代词指代研究的24个hand-crafted特征；然后利用多层感知器（multilayer perception，MLP）融合Bi-LSTM学习到的上下文语义层面特征与hand-crafted特征；最后使用融合的两类特征训练softmax分类器完成维吾尔语人称代词指代消解任务.实验结果表明，充分利用两类特征的优势，维吾尔语人称代词指代消解的F1值达到76.86%.实验验证了Bi-LSTM与单向LSTM、浅层机器学习算法的SVM和ANN相比更具备挖掘隐含上下文深层语义信息的能力，而hand-crafted层面特征的引入，则有效提高指代消解性能.

关键词: 指代消解, 双向长短时记忆网络, 词向量, 深度学习, 维吾尔语, 自然语言处理

Abstract: Specific to the anaphora phenomenon of Uyghur personal pronouns,a deep learning mechanism of Bi-LSTM (Bi-directional long short term memory) network is proposed,which is based on the deep semantic information to resolve anaphora resolution problem in Uyghur personal pronouns.Firstly,make the word embedding which contain semantic and syntactic information as the input of Bi-LSTM,to excavate the implicit semantic features of Uyghur.Secondly,explore the anaphora phenomenon in Uyghur and extract 24 hand-crafted features.Then,use multilayer perception(MLP)to concatenate hand-crafted features and context semantic features.Finally,two types of features are used to train the softmax classifier to complete the task.The experimental results show that,on the basis of full utilization of the advantages of two types of features,the F1 value of anaphora resolution is 76.86%.It is proved that Bi-LSTM is more capable of mining implicit context semantic information than LSTM、SVM as well as ANN,and the introduction of hand-crafted features can effectively improve the performance.

Key words: anaphora resolution, Bi-LSTM, word embedding, deep learning, Uyghur, natural language processing

中图分类号:

TP391

. 基于Bi-LSTM的维吾尔语人称代词指代消解[J]. 电子学报, 2018, 46(7): 1691-1699.

. Anaphora Resolution of Uyghur Personal Pronouns Based on Bi-LSTM[J]. Acta Electronica Sinica, 2018, 46(7): 1691-1699.

参考文献

[1] ZELENKO D,AONE C,TIBBETTS J.Coreference resolution for information extraction[A].Proceedings of the ACL Workshop on Reference Resolution and Its Applications[C].Barcelona,Spain:ACL,2004.9-16.
[2] VAN DEEMTER K,KIBBLE R.On coreferring:coreference in MUC and related annotation schemes[J].Computational Linguistics,2000,26(4):629-637.
[3] MCCARTHY J F,LEHNERT W G.Using decision trees for coreference resolution[A].Proceedings of Fourteenth International Joint Conference on Artificial Intelligence[C].Montreal:IJCAI,2000.1050-1055.
[4] 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.
[5] NG V,CARDIE C.Improving machine learning approaches to coreference resolution[A].Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics[C].Philadelphia:ACL,2002.104-111.
[6] 杨勇,李艳翠,周国栋,等.指代消解中距离特征的研究[J].中文信息学报,2008,22(5):39-44. YANG Y,LI Y C,ZHOU G D,et al.Reaserch on distance information for anaphora resolution[J].Journal of Chinese Information Processing,2008,22(5):39-44.(in Chinese)
[7] 孔芳,周国栋.基于树核函数的中英文代词消解[J].软件学报,2012,34(5):1085-1099. KONG F,ZHOU G D.Pronoun resolution in English and Chinese languages based on tree kernel[J].Journal of Software,2012,34(5):1085-1099.(in Chinese)
[8] 周炫余,刘娟,等.基于测度优化Laplacian SVM的中文指代消解方法[J].电子学报,2016,44(12):3064-3072. ZHOU X Y,LIU J,et al.Chinese anaphora resolution based on metric-optimized Laplacian SVM[J].Acta Electronica Sinica,2016,44(12):3064-3072.(in Chinese)
[9] 奚雪峰,周国栋.基于Deep Learning的代词指代消解[J].北京大学学报(自然科学版),2014,50(1):100-110. XI X F,ZHOU G D.Pronoun resolution based on deep learning[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2014,50(1):100-110.(in Chinese)
[10] MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[J].Advances in Neural Information Processing Systems,2013,26:3111-3119.
[11] KOLEN J,KREMER S.Gradient flow in recurrent nets:the difficulty of learning longterm dependencies[J].Wiley-IEEE Press,2001,28(2):237-243.
[12] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1681-1726.
[13] ZHOU P,SHI W,TIAN J,et al.Attention-based bidirectional long short-term memory networks for relation classification[A].Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics[C].Berlin,Germany:ACL,2016.207-212.
[14] TANG D,QIN B,FENG X,et al.Effective LSTMs for target-dependent sentiment classification[A].Proceedings of the 26th International Conference on Computational Linguistics[C].Osaka,Japan:COLING,2016.3298-3307.
[15] BENGIO Y,DUCHARME R,JEAN,et al.A neural probabilistic language model[J].Journal of Machine Learning Research,2003,3(6):1137-1155.
[16] COLLOBERT R,WESTON J.A unified architecture for natural language processing:deep neural networks with multitask learning[A].Proceedings of the 25th International Conference on Machine Learning[C].Helsinki,Finland:ICML,2008.160-167.
[17] 程适良.现代维吾尔语语法[M].新疆:新疆人民出版社,1996.
[18] MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[J].Advances in Neural Information Processing Systems,2013,26:3111-3119.

基于Bi-LSTM的维吾尔语人称代词指代消解

Anaphora Resolution of Uyghur Personal Pronouns Based on Bi-LSTM

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]	李钦, 刘伟, 牛朝阳, 宝音图, 惠周勃. 低信噪比下基于分裂EfficientNet网络的雷达信号调制方式识别[J]. 电子学报, 2023, 51(3): 675-686.
[2]	范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657.
[3]	张聿远, 闫文君, 张立民. 基于多模态特征融合网络的空时分组码识别算法[J]. 电子学报, 2023, 51(2): 489-498.
[4]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[5]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[6]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[7]	王神龙, 雍宇, 吴晨睿. 基于伪孪生神经网络的低纹理工业零件6D位姿估计[J]. 电子学报, 2023, 51(1): 192-201.
[8]	李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138.
[9]	郭晓轩, 冯其波, 冀振燕, 郑发家, 杨燕燕. 多线激光光条图像缺陷分割模型研究[J]. 电子学报, 2023, 51(1): 172-179.
[10]	贾童瑶, 卓力, 李嘉锋, 张菁. 基于深度学习的单幅图像去雾研究进展[J]. 电子学报, 2023, 51(1): 231-245.
[11]	何滢婕, 刘月峰, 边浩东, 郭威, 张小燕. 基于Informer的电池荷电状态估算及其稀疏优化方法[J]. 电子学报, 2023, 51(1): 50-56.
[12]	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.
[13]	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.
[14]	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.
[15]	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.