·178· 智能系统学报 第14卷 cognition for Chinese social media with word segmenta- ceedings of COLING 2014,the 25th International Confer- tion representation learning[C]//Proceedings of the 54th ence on Computational Linguistics.Dublin,Ireland,2014: Annual Meeting of the Association for Computational Lin- 69-78. guistics.Berlin,Germany,2016:149-155. [15]ZHENG Xiaoqing,CHEN Hanyang,XU Tianyu.Deep [8]MA Xuezhe,HOVY E.End-to-end sequence labeling via learning for Chinese word segmentation and POS bi-directional LSTM-CNNs-CRF[C]//Proceedings of the tagging[C]//Proceedings of 2013 Conference on Empiric- 54th Annual Meeting of the Association for Computation- al Methods in Natural Language Processing.Seattle, al Linguistics.Berlin,Germany,2016:1064-1074. USA2013:647-657. [9]PHAM T H,LE-HONG P.End-to-end recurrent neural [16]SPITKOVSKY VI.ALSHAWI H,JURAFSKY D,et al. network models for Vietnamese named entity recognition: Viterbi training improves unsupervised dependency pars- word-level vs.Character-level[C]//Proceedings of the 15th ing[C]//Proceedings of the 14th Conference on Computa- International Conference of the Pacific Association for tional Natural Language Learning.Uppsala,Sweden Computational Linguistics.Yangon,Myanmar,2017: 2010:9-17 219-232. [17]YADAV V,BETHARD S.A survey on recent advances [10]JEBBARA S,CIMIANO P.Improving opinion-target ex- in named entity recognition from deep learning models traction with character-level word embeddings[C]//Pro- [C]//Proceedings of the 27th International Conference on ceedings of the Ist Workshop on Subword and Character Computational Linguistics.Santa Fe,USA,2018:2145- Level Models in NLP.Copenhagen,Denmark,2017: 2158. 159-167 [11]HAMMERTON J.Named entity recognition with long 作者简介： short-term memory[C]//Proceedings of the 7th Confer- 周浩.男，1993年生，硕士研究 ence on Natural Language Learning at HLT-NAACL 生，主要研究方向为自然语言处理、数 2003.Edmonton,Canada,2003:172-175. 据挖掘、情感分析。 [12]CHEN Xinxiong,XU Lei,LIU Zhiyuan,et al.Joint learn- ing of character and word embeddings[Cl//Proceedings of the 24th International Conference on Artificial Intelli- gence.Buenos Aires,Argentina,2015:1236-1242 [13]YU Mo,DREDZE M.Improving lexical embeddings with 王莉，女，1971年生，教授，博士 生导师，主要研究方向为社会网络计 semantic knowledge[C//Proceedings of the 52nd Annual 算、大数据分析与计算、深度学习。 Meeting of the Association for Computational Linguistics. Baltimore,USA,2014:545-550. [14]DOS SANTOS C N,GATTI M.Deep convolutional neur- al networks for sentiment analysis of short texts[C]//Pro-cognition for Chinese social media with word segmenta￾tion representation learning[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Lin￾guistics. Berlin, Germany, 2016: 149–155. MA Xuezhe, HOVY E. End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF[C]//Proceedings of the 54th Annual Meeting of the Association for Computation￾al Linguistics. Berlin, Germany, 2016: 1064–1074. [8] PHAM T H, LE-HONG P. End-to-end recurrent neural network models for Vietnamese named entity recognition: word-level vs. Character-level[C]//Proceedings of the 15th International Conference of the Pacific Association for Computational Linguistics. Yangon, Myanmar, 2017: 219–232. [9] JEBBARA S, CIMIANO P. Improving opinion-target ex￾traction with character-level word embeddings[C]//Pro￾ceedings of the 1st Workshop on Subword and Character Level Models in NLP. Copenhagen, Denmark, 2017: 159–167. [10] HAMMERTON J. Named entity recognition with long short-term memory[C]//Proceedings of the 7th Confer￾ence on Natural Language Learning at HLT-NAACL 2003. Edmonton, Canada, 2003: 172–175. [11] CHEN Xinxiong, XU Lei, LIU Zhiyuan, et al. Joint learn￾ing of character and word embeddings[C]//Proceedings of the 24th International Conference on Artificial Intelli￾gence. Buenos Aires, Argentina, 2015: 1236–1242. [12] YU Mo, DREDZE M. Improving lexical embeddings with semantic knowledge[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, USA, 2014: 545–550. [13] DOS SANTOS C N, GATTI M. Deep convolutional neur￾al networks for sentiment analysis of short texts[C]//Pro- [14] ceedings of COLING 2014, the 25th International Confer￾ence on Computational Linguistics. Dublin, Ireland, 2014: 69–78. ZHENG Xiaoqing, CHEN Hanyang, XU Tianyu. Deep learning for Chinese word segmentation and POS tagging[C]//Proceedings of 2013 Conference on Empiric￾al Methods in Natural Language Processing. Seattle, USA, 2013: 647–657. [15] SPITKOVSKY V I, ALSHAWI H, JURAFSKY D, et al. Viterbi training improves unsupervised dependency pars￾ing[C]//Proceedings of the 14th Conference on Computa￾tional Natural Language Learning. Uppsala, Sweden, 2010: 9–17. [16] YADAV V, BETHARD S. A survey on recent advances in named entity recognition from deep learning models [C]//Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, USA, 2018: 2145– 2158. [17] 作者简介： 周浩，男，1993 年生，硕士研究 生，主要研究方向为自然语言处理、数 据挖掘、情感分析。 王莉，女，1971 年生，教授，博士 生导师，主要研究方向为社会网络计 算、大数据分析与计算、深度学习。 ·178· 智 能 系 统 学 报 第 14 卷