Skip to main content
Springer Nature Link
Log in

Various Legal Factors Extraction Based on Machine Reading Comprehension

  • Conference paper
  • First Online:
Information Retrieval (CCIR 2021)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 13026))

Included in the following conference series:

Abstract

With the rapid growth of legal cases, professionals are under pressure to go through lengthy documents and grasp informative pieces of text in the limited time. Most of the existing techniques focus on simple legal information retrieval task, such as name or address of the prosecutor or the defendant, which can be easily accomplished with the help of handcrafted patterns or sequence labeling methods. Yet complicated texts always challenge such pattern-based methods and sequence labeling approaches. These texts state the same facts or describe the same events, but they do not share common or similar patterns. In this paper, we design a unified framework to extract legal information in various formats, including directly extracted information (a piece of span) and information that needs to be deduced. The framework follows the methodology to answer questions in machine reading comprehension (MRC) tasks. We treat the extraction fact labels as the counterpart of questions in MRC task and propose several strategies to represent them. We construct several datasets regarding different cases for training and testing. Our best strategy achieves up to 4% enhancement in F1 score on each dataset compared to the MRC baseline.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Buck, C., et al.: Ask the right questions: active question reformulation with reinforcement learning. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 April–3 May 2018, Conference Track Proceedings. OpenReview.net (2018). https://openreview.net/forum?id=S1CChZ-CZ

  2. Che, W., et al.: “N-LTP: a open-source neural Chinese language technology platform with pretrained models. arXiv preprint arXiv:2009.11616 (2020)

  3. Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Long and Short Papers), Minneapolis, Minnesota, vol. 1, pp. 4171–4186. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/N19-1423. https://www.aclweb.org/anthology/N19-1423

  4. Duan, X., et al.: CJRC: a reliable human-annotated benchmark DataSet for Chinese judicial reading comprehension. In: CCL (2019)

    Google Scholar 

  5. Gao, J., Nie, J.-Y.: Towards concept-based translation models using search logs for query expansion (2012). https://www.microsoft.com/en-us/research/publication/towards-concept-based-translation-models-using-search-logs-query-expansion/

  6. Grishman, R.: Information extraction: techniques and challenges. In: Pazienza, M.T. (ed.) SCIE 1997. LNCS, vol. 1299, pp. 10–27. Springer, Heidelberg (1997). https://doi.org/10.1007/3-540-63438-X_2 ISBN 978-3-540-69548-6

    Chapter  Google Scholar 

  7. Hermann, K.M., et al.: Teaching machines to read and comprehend. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, NIPS 2015, Montreal, Canada, vol. 1, pp. 1693–1701. MIT Press (2015)

    Google Scholar 

  8. Levow, G.-A.: The third international Chinese language processing bakeoff: word segmentation and named entity recognition. In: Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, July 2006, pp. 108–117. Association for Computational Linguistics (2006). https://www.aclweb.org/anthology/W06-0115

  9. Li, X., et al.: FLAT: Chinese NER using flat-lattice transformer. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020, pp. 6836–6842. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.acl-main.611. https://www.aclweb.org/anthology/2020.acl-main.611

  10. Li, X., et al.: A unified MRC framework for named entity recognition. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020, pp. 5849–5859. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.acl-main.519. https://www.aclweb.org/anthology/2020.acl-main.519

  11. Liu, B., et al.: A user-centered concept mining system for query and document understanding at Tencent. In: Teredesai, A., et al. (eds.) Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, 4–8 August 2019, pp. 1831–1841. ACM (2019). https://doi.org/10.1145/3292500.3330727

  12. Rajpurkar, P., Jia, R., Liang, P.: Know what you don’t know: unanswerable questions for SQuAD. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Melbourne, Australia, July 2018, pp. 784–789. Association for Computational Linguistics (2018). https://doi.org/10.18653/v1/P18-2124. https://www.aclweb.org/anthology/P18-2124

  13. Rajpurkar, P., et al.: SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas, November 2016, pp. 2383–2392. Association for Computational Linguistics (2016). https://doi.org/10.18653/v1/D16-1264. https://www.aclweb.org/anthology/D16-1264

  14. Su, J.: SimBERT: integrating retrieval and generation into BERT. Technical report (2020)

    Google Scholar 

  15. Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4–9 December 2017, pp. 5998–6008 (2017). https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd05%203c1c4a845aa-Abstract.html

  16. Wu, Y., et al.: Chinese named entity recognition based on multiple features. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT 2005, Vancouver, British Columbia, Canada, pp. 427–434. Association for Computational Linguistics (2005). https://doi.org/10.3115/1220575.1220629

  17. Yan, H., et al.: TENER: adapting transformer encoder for named entity recognition (2019). arXiv:1911.04474 [cs.CL]

  18. Zhang, Y., Yang, J.: Chinese NER using lattice LSTM. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, July 2018, pp. 1554–1564. Association for Computational Linguistics (2018). https://doi.org/10.18653/v1/P18-1144. https://www.aclweb.org/anthology/P18-1144

  19. , vol. 06, pp. 60–66 (2010)

    Google Scholar 

Download references

Acknowledgments

The authors would like to thank all the reviewers for their insight reviews. This paper is funded by National Key R&D Program of China (No.2018YFC0807701).

Author information

Authors and Affiliations

  1. State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, Beijing, China

    Beichen Wang, Ziyue Wang, Baoxin Wang, Dayong Wu, Zhigang Chen, Shijin Wang & Guoping Hu

  2. iFLYTEK AI Research (Hebei), Langfang, China

    Shijin Wang

Authors
  1. Beichen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ziyue Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Baoxin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dayong Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhigang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shijin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Guoping Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ziyue Wang .

Editor information

Editors and Affiliations

  1. Dalian University of Technology, Dalian, China

    Hongfei Lin

  2. Department of Computer Science, Tsinghua University, Beijing, China

    Min Zhang

  3. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

    Liang Pang

Appendix

Appendix

Table 5. Data augmentation of other two datasets. We selected two representative questions from each dataset. We do not translate sentences after data augmentation (DA) because DA is usually a paraphrasing of the original questions, and the English version could remain unchanged.
Full size table
Table 6. Results of general questions, reported in Exact Match(%), F1 score(%), Precision(%) and Recall(%). The meaning of each experiment in this table is the same as that in Table 4. It is noted that the extraction results of the questions whose answer is no in the datasets of recourse for labor remuneration and refusal to execute judgments or rulings are poor, and even the results of many experiments are 0. As shown in Table 2, the questions with negative answer are originally very rare, and we do not build the datasets specifically for this situation, which made it difficult to extract, or simply do not show in the test sets.
Full size table

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, B. et al. (2021). Various Legal Factors Extraction Based on Machine Reading Comprehension. In: Lin, H., Zhang, M., Pang, L. (eds) Information Retrieval. CCIR 2021. Lecture Notes in Computer Science(), vol 13026. Springer, Cham. https://doi.org/10.1007/978-3-030-88189-4_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-88189-4_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-88188-7

  • Online ISBN: 978-3-030-88189-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics