Named entity recognition is a highly relevant research topic in the field of natural language processing owing to its widespread application, which mainly involves three types of nested entities, discontinuous entities and flat named entities. Notably, nested named entities are characterized by one entity containing multiple sub-entities, ambiguous boundary definitions, and flexible structural formats. These features give rise to challenges such as semantic ambiguity, slow decoding efficiency, error propagation, and information loss. Therefore, to effectively address these issues and enhance classification performance, it is critical to integrate information sources such as internal markers, neighbouring word pairs, first and last word pairs, labels, and related spans. This is achieved in the present study via a newly proposed nested named entity recognition model based on triple cross affine attention. The proposed model encodes the input text using the BERT model and Bi-LSTM before extracting relevant features from the input text by applying DCNN. The extracted feature sequences are used as input into the triple cross affine attention module which computes the scores, allowing the model to classify and predict the outputs using the MLP layer. The experimental results demonstrate that the precision, recall, and F1 value metrics of the proposed method outperform other existing benchmark algorithmic models when applied to the ACE2004, ACE2005, and GENIA standard datasets. Additionally, it exhibits superior recognition performance in nested named entity recognition.
BobD. D. V.FlorisF. B.MaxA. V.HessamS.MariusS.IvanaI., et al. (2019). A deep learning framework for unsupervised affine and deformable image registration. Computing Research Repository, 52(0), 128.0–143.0.
2.
DevlinJ.ChangM.LeeK.ToutanovaK. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the NAACLHLT (pp. 4171–4186).
3.
FengH.RuiliW.JunH.YiZ., et al. (2020). Improving entity linking through semantic reinforced entity embeddings. In Annual meeting of the association for computational linguistics, 2020 (pp. 6843–6848).
4.
FuJ.HuangX.LiuP. (2021). SpanNER: Named entity re-/recognition as span prediction. In Proceedings of the annual meeting of the association for computational linguistics (pp. 7183–7195).
5.
FuY.TanC. Q.ChenM. S.HuangS. F.HuangF., et al. (2021). Nested named entity recognition with partially-observed treecrfs. In AAAI conference on artificial intelligence, Vol. 35, (pp. 12839–12847).
6.
HeK.ZhangX.RenS.SunJ. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA (pp. 770–778).
7.
HendrycksD.GimpelK. (2016). Gaussian error linear units (GELUs). arXiv: Learning.
8.
HuangP.ZhaoX.HuM.FangY.LiX.XiaoW. D., et al. (2022). Extract-Select: A span selection framework for nested named entity recognition with generative adversarial training. In Findings of the association for computational linguistics: ACL 2022 (pp. 85–96).
9.
JingyeL.HaoF.JiangL.ShengqiongW.MeishanZ.ChongT.DonghongJ.FeiL., et al. (2022). Unified named entity recognition as word-word relation classification. In AAAI Conference on artificial intelligence (pp. 10965–10973).
10.
KimJ-DOhtaT.TateisiY.TsujiiJ. (2003). Genia corpus–a semantically annotated corpus for bio-textmining. Bioinformatics (Oxford, England), 19(1), i180-–i182.
11.
KimG.SonJ.KimJ.LeeH.LimH. (2021). Enhancing Korean named entity recognition with linguistic tokenization strategies. IEEE Access, 9, 151814.
12.
LampleG.BallesterosM.SubramanianS.KawakamiK.DyerC. (2016). Neural architectures for named entity recognition. In Proceedings of the NAACL (pp. 260–270).
13.
LeP.TitovI. (2018). Improving entity linking by modeling latent relations between mentions. In Proceedings of the ACL (pp. 1595–1604).
14.
LiF.LinZ.ZhangM.JiD. (2021). A span-based model for joint overlapped and discontinuous named entity recognition. In Proceedings of the ACL-IJCNLP (pp. 4814–4828).
15.
LiJ.XuK.LiF.FeiH.RenY.JiD. (2021). MRN: A locally and globally mention-based reasoning network for document-level relation extraction. In Proceedings of the ACL-IJCNLP findings (pp. 1359–1370).
16.
LiuR.WeiJ.JiaC.VosoughiS. (2021). Modulating language models with emotions. In Findings of the ACLIJCNLP (pp. 4332–4339).
17.
LouC.YangS. L.TuK. W. (2022). Nested named entity recognition as latent lexicalized constituency parsing. In Proceedings of the 60th Annual meeting of the association for computational linguistics (Volume 1: Long Papers) (pp. 6183–6198).
18.
LuW.RothD. (2015). Joint mention extraction and classification with mention hypergraphs. In Proceedings of the EMNLP (pp. 857–867).
19.
LuanY.WaddenD.HeL.ShahA.OstendorfM.HajishirziH. (2019). A general framework for information extraction using dynamic span graphs. In Proceedings of the NAACL (pp. 3036–3046).
20.
MaX. Z.EduardH. H. (2016). End-to-end sequence labeling via bi-directional lstm-cnns-crf. In Proceedings of the 54th Annual meeting of the association for computational linguistics, ACL 2016 (pp. 1–12).
21.
MK. A. K.SanjayJ.AmitM.SanjayK. J., et al. (2016). A survey on question answering systems with classification. Journal of King Saud University - Computer and Information Sciences, 28(3), 345–361.
22.
NatawutM.GiuseppeC.SimoneF.OlegR., et al. (2021). Continual learning for named entity recognition. In AAAI Conference on artificial intelligence (pp. 13570–13577).
23.
StrakováJ.StrakaM.HajicJ. (2019). Neural architectures for nested ner through linearization. In Proceedings of the ACL (pp. 5326–5331).
24.
TanC. Q.QiuW.ChenM. S.WangR.HuangF. (2020). Boundary enhanced neural span classification for nested named entity recognition. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34, (pp. 9016–9023).
25.
TangZ.WanB.YangL. (2020). Word-character graph convolution network for Chinese named entity recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 1520–1532.
26.
WanJ.RuD.ZhangW.YuY., et al. (2022). Nested named entity recognition with span-level graphs. In Proceedings of the 60th Annual meeting of the association for computational linguistics (Volume 1: Long Papers) (pp. 892–903).
27.
WangB.LuW. (2018). Neural segmental hypergraphs for overlapping mention recognition. In Proceedings of the EMNLP (pp. 204–214).
28.
WangJ.ShouL. D.ChenK.ChenG. (2020). Pyramid: A layered model for nested named entity recognition. In Proceedings of the 58th Annual meeting of the association for computational linguistics (pp. 5918–5928).
29.
WeiZ. P.SuJ. L.WangY.TianY.ChangY. (2020). A novel cascade binary tagging framework for relational triple extraction. In Proceedings of the ACL (pp. 1476–1488).
30.
YanH.GuiT.DaiJ.GuoQ.ZhangZ.QiuX. (2021). A unified generative framework for various NER subtasks. In Proceedings of the ACL-IJCNLP (pp. 5808–5822).
31.
YangS. L.TuK. W. (2022). Bottom-up constituency parsing and nested named entity recognition with pointer networks. In Proceedings of the 60th Annual meeting of the association for computational linguistics.
32.
YuJ. T.BohnetB.PoesioM. (2020). Named entity recognition as dependency parsing. In Proceedings of the 58th Annual meeting of the association for computational linguistics (pp. 6470–6476).
33.
YuF.KoltunV. (2015). Multi-scale context aggregation by dilated convolutions. In International conference on learning representations.
34.
YuanZ.TanC.HuangS.HuangF. (2022). Fusing heterogeneous factors with triafine mechanism for nested named entity recognition. In Proceedings of the 60th Annual meeting of the association for computational linguistics (Volume 1: Long Papers) (pp. 3174–3186).
35.
ZhengC.CaiY.XuJ.LeungH.-F.XuG. (2019). A boundary-aware neural model for nested named entity recognition. In Proceedings of the EMNLP-IJCNLP (pp. 357–366).
36.
ZhengC.WuZ.WangT.CaiY.LiQ. (2021). Object-Aware Multimodal Named Entity Recognition in Social Media Posts With Adversarial Learning. IEEE Transactions on Multimedia, 23, 2520–2532.
37.
ZhongZ.ChenD. (2021). A frustratingly easy approach for entity and relation extraction. In North American association for computational linguistics (NAACL).
