联合多模态与多跨度特征的嵌套命名实体识别

doi:10.3778/j.issn.1673-9418.2302029

摘要/Abstract

摘要： 嵌套命名实体识别（NNER）因日趋重要的现实意义成为信息抽取的研究热点。但是，由于语料资源匮乏、穷举窗口受限以及跨度特征缺失等问题，面向垂直领域的NNER研究进展缓慢且存在实体识别错误或遗漏的问题。针对上述问题，提出一种以矿物学为研究背景，融合语料感知词典的垂直领域NNER模型。首先，结合点互信息、词频逆文本频率算法与注意力机制自动集成语料感知词典，同时扩展锚文本知识提升模型的训练精度。其次，从共享视角出发，设计三种多模态信息的融合策略，训练编码器学习字符、字形、词汇的扩展向量表示，通过三重积运算和切片注意力机制，筛选整合由多层感知机捕捉到的私有表征，缩小异质特征的空间差距。再次，以自底向上的层级架构确定跨度间的上下文关联，生成建议跨度集合，以双仿射机制和线性分类器获得目标跨度与相邻跨度、目标跨度内部表征、目标跨度边界等特征。最后，为目标跨度分配对应的实体类型标签。在六项数据集上的实验结果表明，相比于基线模型，提出的方法实现了显著的性能提升，能有效提升低资源场景下的NNER任务效果。

关键词: 嵌套命名实体识别, 多模态, 多任务, 远程监督, 矿物学

Abstract: Nested named entity recognition (NNER) has become a research hotspot in information extraction because of its increasingly important practical significance. However, due to the shortage of corpus resources, limited exhaustive windows, missing span features, etc., NNER research in vertical field has made slow progress and there are problems of entity recognition errors or omissions. To solve these problems, a vertical field NNER model based on mineralogy and corpus awareness dictionary is proposed. Firstly, the point mutual information, word frequency inverse text frequency algorithm and attention mechanism are combined to automatically integrate the corpus awareness dictionary, and the anchor text knowledge is used to improve the training accuracy of the model. Secondly, from the shared perspective, three multi-modal information fusion strategies are designed to train the encoder to learn the extended vector representation of character, glyph and vocabulary. Through triple product operation and slicing attention mechanism, the private representations captured by the multi-layer perceptron are screened and integrated to narrow the spatial gap of heterogeneous features. Thirdly, the context association between spans is determined by a bottom-up hierarchical architecture, and the proposed span set is generated. The characteristics of target span and adjacent span, target span internal characterization, target span boundary, etc. are obtained by double affine mechanism and linear classifier. Finally, the corresponding entity type label is assigned to the target span. Experimental results on six datasets show that compared with baseline model, the proposed method achieves significant performance improvement and can effectively improve the NNER task effect in low-resource scenarios.

Key words: nested named entity recognition, multi-modal, multi-task, distant supervision, mineralogy

邱云飞, 邢浩然, 于智龙, 张文文. 联合多模态与多跨度特征的嵌套命名实体识别[J]. 计算机科学与探索, 2024, 18(6): 1613-1626.

QIU Yunfei, XING Haoran, YU Zhilong, ZHANG Wenwen. Nested Named Entity Recognition Combining Multi-modal and Multi-span Features[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(6): 1613-1626.

参考文献

[1] ROJAS M, BRAVO-MARQUEZ F, DUNSTAN J. Simple yet powerful: an overlooked architecture for nested named entity recognition[C]//Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Oct 12-17, 2022: 2108-2117.
[2] SHEN Y, MA X, TAN Z, et al. Locate and label: a two- stage identifier for nested named entity recognition[C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Aug 1-6, 2021.Stroudsburg: ACL, 2021: 2782-2794.
[3] WU S, SONG X, FENG Z. MECT: multi-metadata embed- ding based cross-transformer for Chinese named entity recognition[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Aug 1-6, 2021. Stroudsburg: ACL, 2021: 1529-1539.
[4] LUO Y, ZHAO H. Bipartite flat-graph network for nested named entity recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Jul 6-8, 2020. Stroudsburg: ACL, 2020: 6408-6418.
[5] JU M, MIWA M, ANANIADOU S. A neural layered model for nested named entity recognition[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2018: 1446-1459.
[6] HUANG P, ZHAO X, HU M, et al. Extract-Select: a span selection framework for nested named entity recognition with generative adversarial training[C]//Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg: ACL, 2022: 85-96.
[7] YANG S, TU K. Bottom-up constituency parsing and nested named entity recognition with pointer networks[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2022: 2403-2416.
[8] YUAN Z, TAN C, HUANG S, et al. Fusing heterogeneous factors with triaffine mechanism for nested named entity recognition[C]//Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg: ACL, 2022: 3174-3186.
[9] GU Y, QU X, WANG Z, et al. Delving deep into regularity: a simple but effective method for Chinese named entity recog-nition[C]//Findings of the Association for Computational Lin-guistics: ACL 2022. Stroudsburg: ACL, 2022: 1863-1873.
[10] WU S, SHEN Y, TAN Z, et al. Propose-and-Refine: a two-stage set prediction network for nested named entity recognition[C]//Proceedings of the 31st International Joint Conference on Artificial Intelligence, Vienna, Jul 23-29, 2022: 4418-4424.
[11] LIU W, FU X, ZHANG Y, et al. Lexicon enhanced Chinese sequence labeling using BERT adapter[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2021: 5847-5858.
[12] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre- training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Jun 2-7, 2019. Stroudsburg: ACL, 2019: 4171-4186.
[13] LI X, FENG J, MENG Y, et al. A unified MRC framework for named entity recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 5849-5859.
[14] XUAN Z, BAO R, JIANG S. FGN: fusion glyph network for Chinese named entity recognition[C]//Proceedings of the 5th China Conference on Knowledge Graph and Semantic Computing, Aug 24-27, 2021: 28-40.
[15] LI X N, YAN H, QIU X P, et al. FLAT: Chinese NER using flat-lattice transformer[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Washington, Jul 5-10, 2020. Stroudsburg: ACL, 2020: 6836-6842.
[16] SUN Z, LI X, SUN X, et al. ChineseBERT: Chinese pretrai- ning enhanced by glyph and Pinyin information[C]//Proce- edings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2021: 2065-2075.
[17] YANG Z, MA J, CHEN H, et al. HiTRANS: a hierarchical transformer network for nested named entity recognition[C]//Findings of the Association for Computational Linguistics: Empirical Methods in Natural Language Processing 2021. Stroudsburg: ACL, 2021: 124-132.
[18] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 99: 2999-3007.
[19] HONGYING Z, WENXIN L, KUNLI Z, et al. Building a pediatric medical corpus: word segmentation and named entity annotation[J]. Chinese Lexical Semantics, 2021, 21: 652-664.
[20] PENG N, DREDZE M. Named entity recognition for Chinese social media with jointly trained embeddings[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2015: 548-554.
[21] WEISCHEDEL R, PRADHAN S, RAMSHAW L, et al. Ontonotes release 4.0[EB/OL]. [2022-11-25]. https://doi.org/10.35111/gfjf-7r50.
[22] WALKER C, STRASSEL S, MEDERO J, et al. ACE 2005 multilingual training corpus[J]. Progress of Theoretical Physics Supplement, Philadelphia, 2006, 110: 261-276.
[23] KIM J D, OHTA T, TATEISI Y, et al. GENIA corpus—a semantically annotated corpus for bio-textmining[J]. Bio-informatics, 2003, 19: 180-182.
[24] SPRINGER, CHAM, WANG X, et al. CHEMNER: fine- grained chemistry named entity recognition with ontology-guided distant supervision[C]//Proceedings of the 2021 Con-ference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2021: 5227-5240.
[25] ZHANG Y, YANG J. Chinese NER using lattice LSTM [C]//Proceedings of the 56th Annual Meeting of the Ass- ociation for Computational Linguistics, Melbourne, Jul 15-20, 2018. Stroudsburg: ACL, 2018: 1554-1564.
[26] YU J, BOHNET B, POESIO M. Named entity recognition as dependency parsing[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 6470-6476.
[27] PENNINGTON J, SOCHER R, MANNING C D. GloVe: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2014: 1532-1543.
[28] CHIU B, CRICHTON G, KORHONEN A, et al. How to train good word embeddings for biomedical NLP[C]//Proceedings of the 15th Workshop on Biomedical Natural Language Processing. Stroudsburg: ACL, 2016: 166-174.
[29] LEE J, YOON W, KIM S, et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining[J]. Bioinformatics, 2020, 36(4): 1234-1240.
[30] SONG Y, SHI S, LI J, et al. Directional skip-gram: expli- citly distinguishing left and right context for word embed-dings[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2018: 175-180.