当前中文命名实体识别方法仅采用字级别或词级别特征方法进行识别,不能兼顾字和词级别的优点,难以获取足够的字形或者词义信息。针对此问题,该文提出一种基于多级别特征感知网络的中文命名实体识别方法。首先提出一种双通道门控卷积神经网络,通过感知字级别特征,在减少了未登录词的同时,也表示了字的字形信息。同时,为了获取词语的词义信息,该文在词级别的特征中嵌入对应位置信息。为了赋予实体更多的权重,该文利用自注意力机制感知带有位置信息的词级别特征。进一步,将上述得到的字级别和词级别信息融合,全面表示句子的语义信息。由于采用字词结合的方法容易产生冗余信息,该文设计一种门控机制的Highway网络,来过滤冗余信息,减少冗余信息对命名实体识别的影响,再结合条件随机场学习到句子中的约束条件实现中文命名实体的识别。实验结果表明,该文所提出的方法总体上优于目前主流的中文命名实体识别方法。
Abstract
Currently most Chinese named entity recognition methods use either Chinese character-level or word-level feature-aware networks for recognition. In this condition, the advantages of both character-level and word-level methods cannot be combined together, which makes it difficult to obtain adequate information of the Chinese character glyphs or the word semantics. This paper proposes a Chinese named entity recognition method based on multi-level feature-aware network. Firstly, a two-channel gated convolutional neural network is proposed to perceive Chinese character-level features, which alleviates the OOV(out-of-vocabulary) words and obtains the glyph information of Chinese characters. To apply entities with more weights, the self-attention mechanism is used to perceive the word semantics with position information. Therefore, the Chinese character-level and word-level information obtained above are fused, with a Highway network based on the gating mechanism to filter the redundant information. Finally, the Conditional Random Field is applied to learn the constraints in the sentence. The experimental results show that the proposed algorithm performs better than the current mainstream Chinese named entity recognition algorithms.
关键词
命名实体识别 /
双通道门控卷积 /
自注意力机制 /
Highway网络
{{custom_keyword}} /
Key words
named entity recognition /
dual-channel gated convolutional /
self-attention mechanism /
Highway network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Lee J, Seo S, Choi Y S. Semantic relation classification via bidirectional LSTM networks with entity-aware attention using latent entity typing[J]. Symmetry, 2019, 11 (6): 785-796.
[2] Zhang B, Li X, Xu X, et al. Knowledge guided capsule attention network for aspect-based sentiment analysis[J]. IEEE/ACM transactions on audio, speech, and language processing, 2020, 28: 2538-2551.
[3] Sun H, Wang R, Chen K, et al. Unsupervised neural machine translation with cross-lingual language representation agreement[J]. IEEE/ACM Transactions on Audio, Speech, Language Processing, 2020, 28 (99): 1170-1182.
[4] Zhou G. Named entity recognition using an HMM-based chunk tagger[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, 2001: 473-480.
[5] Mccallum A, Freitag D, Pereira F C N. Maximum entropy Markov models for information extraction and segmentation[C]//Proceedings of the 17th International Conference on Machine Learning, 2000: 591-598.
[6] Lafferty J, Mccallum A, Pereira F C N. Conditional random fields: Probabilistic models for segmenting and labeling sequence data[C]//Proceddings of the 18th International Conference on Machine Learning, 2001: 282-289.
[7] Huang Z, Xu W, Yu K. Bidirectional LSTM-CRF models for sequence tagging[J]. arXiv: 01991, 2015.
[8] JIN Y, XIE J, GUO W, et al. LSTM-CRF neural network with gated self attention for Chinese NER[J]. IEEE Access, 2019: 136694-136703.
[9] Zhang N, Xu G, Zhang Z, et al. MIFM: Multi-granularity information fusion model for Chinese named entity recognition[J]. IEEE Access, 2019: 181648-181655.
[10] 冯艳红, 于红, 孙庚, 等. 基于BlSTM的命名实体识别方法[J].计算机科学,2018, 45 (2): 261-268.
[11] Tang Z, Wan B, Yang L.Word-character graph convolution network for Chinese named entity recognition[J]. IEEE/ACM Transactions on Audio, Speech, Language Processing, 2020: 1520-1532.
[12] Wang C, Wang H, Zhuang H, et al. Chinese medical named entity recognition based on multi-granularity semantic dictionary and multimodal tree[J]. Journal of Biomedical Informatics, 2020, 111: 103583.
[13] Hu H, Zhang H. Chinese named entity recognition with CRFs: two levels[C]//Proceedings of the International Conference on Computational Intelligence & Security, 2008.
[14] 周俊昊. 基于深度学习的命名实体识别方法研究[D]. 无锡: 江南大学硕士学位论文, 2021.
[15] Lin C Y, Xue N, Zhao D, et al. Character-Based LSTM-CRF with radical-level features for Chinese named entity recognition[J]. Lecture Notes in Computer Science, 2016: 239-250.
[16] Jia Y, Xu X. Chinese named entity recognition based on CNN-BiLSTM-CRF[C]//Proceedings of the 9th IEEE International Conference on Software Engineering and Service Science, 2018: 1-4.
[17] Peters M E, Ammar W, Bhagavatula C, et al.Semi-supervised sequence tagging with bidirectional language models[J]. arXiv: 00108, 2017.
[18] 盛剑, 向政鹏, 秦兵, 等. 多场景文本的细粒度命名实体识别[J]. 中文信息学报, 2019, 33 (6): 81-87.
[19] Zhu Y, Wang G, Karlsson B F. CAN-NER: Convolutional attention network for Chinese named entity recognition[C]//Proceddings of the Conference of the North American Chapter of the Association for Computational Linguistics, 2019: 3384-3393.
[20] Hochreiter S, Schmidhuber. Long short-term memory[J]. Neural Computation, 1997: 1735-1780.
[21] Strubell E, Verga P, Belanger D, et al. Fast and accurate entity recognition with iterated dilated convolutions[C]//Proceddings of the Conference on Empirical Methods in Natural Language Processing, 2017: 2670-2680.
[22] Dauphin Y N, Fan A, Auli M, et al. Language modeling with gated convolutional networks[C]//Proceedings of the 34th International Conference on Machine Learning, 2017: 933-941.
[23] Forney G D.The viterbi algorithm[C]//Proceedings of the IEEE, 1973: 268-278.
[24] 殷章志, 李欣子, 黄德根, et al. 融合字词模型的中文命名实体识别研究[J]. 中文信息学报, 2019, 33 (11):95-106.
[25] Cao P, Chen Y, Liu K, et al. Adversarial transfer learning for Chinese named entity recognition with self-attention mechanism[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018.
[26] Zhang N, Li F, Xu G, et al. Chinese NER using dynamic meta-embeddings[J]. IEEE Access, 2019: 64450-64459.
[27] 王蕾, 谢云, 周俊生, 等. 基于神经网络的片段级中文命名实体识别[J]. 中文信息学报,2018, 32 (3): 84-90.
[28] 张海楠, 伍大勇, 刘悦. 基于深度神经网络的中文命名实体识别[J]. 中文信息学报, 2017, 31 (4): 28-35.
[29] Zhang Y, Yang J. Chinese NER using lattice LSTM[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1554-1564.
[30] 陈茹, 卢先领. 融合空洞卷积神经网络与层次注意力机制的中文命名实体识别[J]. 中文信息学报, 2020 (8): 237-242.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61673193,62076110);江苏省自然科学基金(BK20181341);中国博士后科学基金(2017M621625)
{{custom_fund}}
PDF(2234 KB)
