Anaphora Resolution of Uyghur Personal Pronouns Based on Bi-LSTM

doi:10.3969/j.issn.0372-2112.2018.07.022

PDF(1047 KB)

ACTA ELECTRONICA SINICA ›› 2018, Vol. 46 ›› Issue (7) : 1691-1699. DOI: 10.3969/j.issn.0372-2112.2018.07.022

Anaphora Resolution of Uyghur Personal Pronouns Based on Bi-LSTM

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

Author information +

History +

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

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

TIAN Sheng-wei, QIN Yue, YU Long, Turgun Ibrahim, FENG Guan-jun. Anaphora Resolution of Uyghur Personal Pronouns Based on Bi-LSTM[J]. Acta Electronica Sinica, 2018, 46(7): 1691-1699. https://doi.org/10.3969/j.issn.0372-2112.2018.07.022

References

[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.

Funding

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)