1.School of Software, Xinjiang University, Urumqi, Xinjiang 830091, China; 2.College of Information Science and Engineering, Xinjiang University, Urumqi, Xinjiang 830046, China
Abstract：This paper proposes an Uyghur nouns anaphora resolution model ATT-IndRNN-CNN based on Attention Mechanism (ATT), Independently Recurrent Neural Network (IndRNN) and Convolutional Neural Network (CNN). According to the grammar and semantic structure of Uyghur, 17 rules and semantic information features are extracted. The attention mechanism is applied to select the features via the correlation between the features and the resolution results. The results are input into IndRNN and CNN to obtain the global features and local features in the context, respectively. Finally, the two types of features are merged and softmax is used to classify the resolution task. The experimental results show that the proposed method is better than the classical models, achieving the precision of 87.23%, the recall of 88.80%, and the F-measure of 88.04%.
[1]Van deemter K. Kibble R. On coreferring: Coreference in MUC and related annotation schemes [J]. Computational Linguistics,2006,26(4): 629-637. [2]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. [3]王厚峰. 指代消解的基本方法和实现技术[J]. 中文信息学报, 2002, 16(6):9-17. [4]Mc Carthy J F, Lehnert W G. Using decision trees for coreference resolution[C]//Proceedings of the 14th International Joint Conference on Artificial Intelligence, 1995, 47(1):1050-1055. [5]Soon W M, Ng H T, Lim D C Y. A machine learning approach to coreference resolution of noun phrases[M]. MIT Press, 2001. [6]Ng V, Cardie C. Improving machine learning approaches to coreference resolution[C]//Processing of the 40th Annual Meeting on Association for Computational Linguistics. 2002:104-111. [7]Yang X, Su J, Tan C L. A Twin-candidate model for learning-based anaphora resolution[J]. Computational Linguistics, 2008, 34(3):327-356. [8]Kong F, Zhou G D, Zhu Q. Employing the centering theory in pronoun resolution from the semantic perspective[C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2. 2009:987-996. [9]郭志立. 人称代词指代主体的辨析及其在摘要提取中的应用[C].中文信息处理国际会议, 1998. [10]马彦华, 王能忠. 汉语中人称代词指代问题研究[C].中文信息处理国际会议, 1998. [11]许敏, 王能忠, 马彦华. 汉语中指代问题的研究及讨论[J]. 西南师范大学学报(自然科学版), 1999(6):633-637. [12]王厚峰. 指代消解的基本方法和实现技术[J]. 中文信息学报, 2002, 16(6):9-17. [13]王厚峰, 何婷婷. 汉语中人称代词的消解研究[J]. 计算机学报, 2001, 24(2):136-143. [14]王厚峰, 梅铮. 鲁棒性的汉语人称代词消解[J]. 软件学报, 2005, 16(5):700-707. [15]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. [16]李敏, 禹龙, 田生伟,等. 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(11):1984-1992. [17]Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of Advances in Neural Information Processing Systems, 2013, 26:3111-3119. [18]Mnih V, Heess N, Graves A, et al. Recurrent models of visual attention[C]//Proceedings of NIPS 2014, 2014, 3:2204-2212. [19]Bandanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv: 2014. [20]Li S, Li W, Cook C, et al. Independently recurrent neural network (IndRNN): Building a longer and deeper RNN[J]. arXiv preprint arXiv:1803,04831, 2018.
2019, Vol. 33 
