Distantly Supervised Named Entity Recognition Combined with Prototypical Networks

被引：0
|
作者：
Luo S. [1 ]
Lin Z. [1 ]
Pan L. [1 ]
Wu Z. [1 ]
机构：
[1] School of Information and Electronics, Beijing Institute of Technology, Beijing
来源：
Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology | 2023年 / 43卷 / 04期
关键词：
automatic corpus annotation; distant supervision; named entity recognition; positive-unlabeled learning{PUL); prototypical network;
D O I：
10.15918/j.tbit1001-0645.2022.098
中图分类号：
学科分类号：
摘要：
Aiming at the problem of entity category labeling errors in the process of using distant supervision to label text entities, it is difficult for the model to effectively distinguish the category characteristics of each entity and affect the accuracy of the model. A named entity recognition （NER）method was proposed in this paper. It was designed to use pre-trained prototypical network coding to correctly label entities to generate category prototype representations, and to filter those far away samples from category prototypes in the corpus. Experiments show that the use of the prototype network can effectively improve the annotation quality of the corpus and improve the performance of the model. © 2023 Beijing Institute of Technology. All rights reserved.
引用
收藏
页码：410 / 416
页数：6
相关论文
共 20 条
  • [1] LUO Senlin, YANG Junnan, PAN Limin, Et al., Text semantic matching method for information and communication (ICT) supply chain network portrait construction, Transactions of Beijing Institute of Technology, 41, 8, pp. 864-872, (2021)
  • [2] PAN Limin, LI Xiaoya, LUO Senlin, Et al., Double-channel GAN with multi-level semantic correlation for event detection, Transactions of Beijing Institute of Technology, 41, 3, pp. 295-302, (2021)
  • [3] LUO Senlin, LI Dongchao, WU Zhouting, Et al., Online protest prediction with time-series text and high-order interactive topology, Transactions of Beijing Institute of Technology, 40, 11, pp. 1245-1252, (2020)
  • [4] CHIU J P C, Nichols E., Named entity recognition with bidirectional LSTM-CNNs, Transactions of the Association for Computational Linguistics, 4, pp. 357-370, (2016)
  • [5] YANG Y, CHEN W, LI Z, Et al., Distantly supervised ner with partial annotation learning and reinforcement learning, Proceedings of the 27th International Conference on Computational Linguistics, pp. 2159-2169, (2018)
  • [6] PENG M, XING X, ZHANG Q, Et al., Distantly supervised named entity recognition using positive-unlabeled learning, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2409-2419, (2019)
  • [7] LIU S, SUN Y, LI B, Et al., HAMNER: headword amplified multi-span distantly supervised method for domain specific named entity recognition, Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), pp. 8401-8408, (2020)
  • [8] YANG P, LIU W, YANG J Y H., Positive unlabeled learning via wrapper-based adaptive sampling, IJCAI.New York: International Joint Conferences on Artificial Intelligence, pp. 3273-3279, (2017)
  • [9] LI J, SHANG S, SHAO L., Metaner: Named entity recognition with meta-learning, Proceedings of The Web Conference 2020, pp. 429-440, (2020)
  • [10] FRITZLER A, LOGACHEVA V, KRETOV M., Few-shot classification in named entity recognition task, Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, pp. 993-1000, (2019)
12