Skip to main content
SpringerLink
Log in

Enhanced Named Entity Recognition with Semantic Dependency

  • Conference paper
  • First Online:
PRICAI 2021: Trends in Artificial Intelligence (PRICAI 2021)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13032))

Included in the following conference series:

Abstract

Dependency-based models for the named entity recognition (NER) task have shown promising results by capturing long-distance relationships between words in a sentence. However, while existing models focus on the syntactic dependency between entities, we are unaware of any work that considers semantic dependency. In this work, we study the usefulness of semantic dependency information for NER. We propose a NER model that is guided by semantic dependency graphs instead of syntactic dependency trees. The extensive experiments illustrate the effectiveness of the proposed model and the advantages of semantic dependency over syntactic dependency for NER. Also, it shows correlations between the NER performance and the semantic dependency annotations qualities.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    HanLP: https://github.com/hankcs/HanLP.

  2. 2.

    SuPar: https://github.com/yzhangcs/parser.

  3. 3.

    The named entity tags use the BIO labeling scheme: B-LOC labels the beginning of a location entity, I-LOC represents the inside word of the named entity, and O-LOC means outside a named entity.

  4. 4.

    TEXT is the textbook corpus from SemEval-2016 Task 9, DM is the DELPH-IN corpus from SemEval-2015 Task 18, PAS is the Enju corpus from SemEval-2015 Task 18, PSD is the Prague corpus from SemEval-2015 Task 18, and LAS is the English Penn Treebank (PTB) corpus [15].

References

  1. Aguilar, G., Solorio, T.: Dependency-aware named entity recognition with relative and global attentions (2019)

    Google Scholar 

  2. Akbik, A., Blythe, D., Vollgraf, R.: Contextual string embeddings for sequence labeling. In: Proceedings of COLING-18, pp. 1638–1649 (2018)

    Google Scholar 

  3. Che, W., Shao, Y., Liu, T., Ding, Y.: SemEval-2016 task 9: Chinese semantic dependency parsing. In: Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2016, San Diego, CA, USA, 16–17 June 2016, pp. 1074–1080. ACL (2016)

    Google Scholar 

  4. Dong, L., Lapata, M.: Coarse-to-fine decoding for neural semantic parsing. In: Proceedings of ACL-18, pp. 731–742 (2018)

    Google Scholar 

  5. Finkel, J.R., Grenager, T., Manning, C.D.: Incorporating non-local information into information extraction systems by Gibbs sampling. In: Proceedings of ACL-05, pp. 363–370 (2005)

    Google Scholar 

  6. Grave, E., Bojanowski, P., Gupta, P., Joulin, A., Mikolov, T.: Learning word vectors for 157 languages. In: Proceedings of LREC-18 (2018)

    Google Scholar 

  7. Hajic, J., et al.: The CoNLL-2009 shared task: syntactic and semantic dependencies in multiple languages. In: Proceedings of CoNLL-09, pp. 1–18 (2009)

    Google Scholar 

  8. Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging (2015)

    Google Scholar 

  9. Jie, Z., Lu, W.: Dependency-guided LSTM-CRF for named entity recognition. In: Proceedings of EMNLP-19, pp. 3860–3870 (2019)

    Google Scholar 

  10. Jie, Z., Muis, A.O., Lu, W.: Efficient dependency-guided named entity recognition. In: Proceedings of AAAI-17, pp. 3457–3465 (2017)

    Google Scholar 

  11. Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of ICML-01, pp. 282–289 (2001)

    Google Scholar 

  12. Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. In: Proceedings of NAACL-HLT-16, pp. 260–270 (2016)

    Google Scholar 

  13. Ling, X., Weld, D.S.: Fine-grained entity recognition. In: Proceedings of AAAI-12 (2012)

    Google Scholar 

  14. Marcheggiani, D., Titov, I.: Encoding sentences with graph convolutional networks for semantic role labeling. In: Proceedings of EMNLP-17, pp. 1506–1515 (2017)

    Google Scholar 

  15. Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of English: the penn treebank. Comput. Linguistics 19(2), 313–330 (1993)

    Google Scholar 

  16. Miwa, M., Bansal, M.: End-to-end relation extraction using LSTMs on sequences and tree structures. CoRR abs/1601.00770 (2016)

    Google Scholar 

  17. Nie, Y., Tian, Y., Song, Y., Ao, X., Wan, X.: Improving named entity recognition with attentive ensemble of syntactic information (2020)

    Google Scholar 

  18. Oepen, S., et al.: SemEval 2015 task 18: broad-coverage semantic dependency parsing. In: Proceedings of SemEval@NAACL-HLT-15, pp. 915–926 (2015)

    Google Scholar 

  19. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of EMNLP-14, pp. 1532–1543 (2014)

    Google Scholar 

  20. Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of NAACL-HLT-18, pp. 2227–2237 (2018)

    Google Scholar 

  21. Pradhan, S., et al.: Towards robust linguistic analysis using OntoNotes. In: Proceedings of CoNLL-13, pp. 143–152 (2013)

    Google Scholar 

  22. Ratinov, L., Roth, D.: Design challenges and misconceptions in named entity recognition. In: Proceedings of CoNLL-09, pp. 147–155 (2009)

    Google Scholar 

  23. Sang, E.F.T.K., Meulder, F.D.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Proceedings of CoNLL-03, pp. 142–147 (2003)

    Google Scholar 

  24. Sasano, R., Kurohashi, S.: Japanese named entity recognition using structural natural language processing. In: Proceedings of IJCNLP-08, pp. 607–612 (2008)

    Google Scholar 

  25. Shen, W., Han, J., Wang, J., Yuan, X., Yang, Z.: SHINE+: a general framework for domain-specific entity linking with heterogeneous information networks. IEEE Trans. Knowl. Data Eng. 30(2), 353–366 (2018)

    Article  Google Scholar 

  26. Wang, C., Cho, K., Kiela, D.: Code-switched named entity recognition with embedding attention. In: Proceedings of Workshop on Computational Approaches to Linguistic Code-Switching, pp. 154–158 (2018)

    Google Scholar 

  27. Zhang, M.S.: A survey of syntactic-semantic parsing based on constituent and dependency structures. SCIENCE CHINA Technol. Sci. 63(10), 1898–1920 (2020). https://doi.org/10.1007/s11431-020-1666-4

    Article  Google Scholar 

  28. Zhang, Y., Qi, P., Manning, C.D.: Graph convolution over pruned dependency trees improves relation extraction. In: Proceedings of EMNLP-18, pp. 2205–2215 (2018)

    Google Scholar 

Download references

Acknowledgements

This work is supported by the funding of State Key Laboratory of Communication Content Cognition (A32002) and Key Research and Development Program of Hubei Province (No. 2020BAB026).

Author information

Authors and Affiliations

  1. State Key Laboratory of Communication Content Cognition, Beijing, China

    Peng Wang & Xiaowang Zhang

  2. College of Intelligence and Computing, Tianjin University, Tianjin, China

    Peng Wang, Xiaowang Zhang & Zhiyong Feng

  3. School of Information and Communication Technology, Griffith University, Brisbane, Australia

    Zhe Wang & Kewen Wang

Authors
  1. Peng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhe Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaowang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kewen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhiyong Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaowang Zhang .

Editor information

Editors and Affiliations

  1. MIMOS Berhad, Kuala Lumpur, Malaysia

    Duc Nghia Pham

  2. Sirindhorn International Institute of Science and Technology, Thammasat University, Mueang Pathum Thani, Thailand

    Thanaruk Theeramunkong

  3. Data61, CSIRO, Brisbane, QLD, Australia

    Guido Governatori

  4. Department of Philosophy, Tsinghua University, Beijing, China

    Fenrong Liu

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wang, P., Wang, Z., Zhang, X., Wang, K., Feng, Z. (2021). Enhanced Named Entity Recognition with Semantic Dependency. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13032. Springer, Cham. https://doi.org/10.1007/978-3-030-89363-7_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-89363-7_22

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-89362-0

  • Online ISBN: 978-3-030-89363-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation