Skip to main content
SpringerLink
Log in

Multilevel Entity-Informed Business Relation Extraction

  • Conference paper
  • First Online:
Natural Language Processing and Information Systems (NLDB 2021)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 12801))

  • 1633 Accesses

Abstract

This paper describes a business relation extraction system that combines contextualized language models with multiple levels of entity knowledge. Our contributions are three-folds: (1) a novel characterization of business relations, (2) the first large English dataset of more than 10k relation instances manually annotated according to this characterization, and (3) multiple neural architectures based on BERT, newly augmented with three complementary levels of knowledge about entities: generalization over entity type, pre-trained entity embeddings learned from two external knowledge graphs, and an entity-knowledge-aware attention mechanism. Our results show an improvement over many strong knowledge-agnostic and knowledge-enhanced state of the art models for relation extraction.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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.

    https://github.com/Geotrend-research/business-relation-dataset.

  2. 2.

    We consider textual contents from various sources and formats excluding those retrieved from social media, e-commerce, and code versioning websites.

  3. 3.

    The set of keywords have been chosen by business intelligence experts.

  4. 4.

    https://isahit.com/en/.

  5. 5.

    https://github.com/facebookresearch/BLINK.

  6. 6.

    https://huggingface.co/bert-base-cased.

  7. 7.

    All the hyperparameters were tuned on a validation set (10% of the train set).

  8. 8.

    Among existing entity-informed models (cf. Sect. 2), at the time of performing these experiments, and as far as we know, only KnowBert and ERNIE were actually available to the research community. In this paper, we compare with Knowbert as it achieved the best results on the TACRED dataset (71.50% on F1-score) when compared to ERNIE (67.97%) [25].

  9. 9.

    We also experimented with Entity-Attention-BiLSTM following [10] but the results were not conclusive.

References

  1. Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC/ISWC -2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-76298-0_52

    Chapter  Google Scholar 

  2. Braun, D., Faber, A., Hernandez-Mendez, A., Matthes, F.: Automatic relation extraction for building smart city ecosystems using dependency parsing. In: Proceedings of NL4AI@ AI* IA, pp. 29–39. CEUR-WS.org (2018)

    Google Scholar 

  3. Camacho-Collados, J., Pilehvar, M.T., Navigli, R.: Nasari: integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities. Artif. Intell. 240, 36–64 (2016)

    Article  MathSciNet  Google Scholar 

  4. Collovini, S., Gonçalves, P.N., Cavalheiro, G., Santos, J., Vieira, R.: Relation extraction for competitive intelligence. In: Quaresma, P., Vieira, R., Aluísio, S., Moniz, H., Batista, F., Gonçalves, T. (eds.) PROPOR 2020. LNCS (LNAI), vol. 12037, pp. 249–258. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-41505-1_24

    Chapter  Google Scholar 

  5. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, no. 1 (2019)

    Google Scholar 

  6. Gupta, P., Rajaram, S., Schütze, H., Runkler, T.: Neural relation extraction within and across sentence boundaries. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6513–6520 (2019)

    Google Scholar 

  7. Hendrickx, I., et al.: SemEval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals. In: Proceedings of the 5th International Workshop on Semantic Evaluation, pp. 33–38. ACL (2010)

    Google Scholar 

  8. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  9. Lau, R., Zhang, W.: Semi-supervised statistical inference for business entities extraction and business relations discovery. In: Proceedings of SIGIR Workshop, pp. 41–46 (2011)

    Google Scholar 

  10. Lee, J., Seo, S., Choi, Y.S.: Semantic relation classification via bidirectional LSTM networks with entity-aware attention using latent entity typing. Symmetry 11(6), 785 (2019)

    Article  Google Scholar 

  11. Li, B.Z., Min, S., Iyer, S., Mehdad, Y., Yih, W.T.: Efficient one-pass end-to-end entity linking for questions. In: Proceedings of EMNLP, pp. 6433–6441 (2020)

    Google Scholar 

  12. Li, J., Huang, G., Chen, J., Wang, Y.: Dual CNN for relation extraction with knowledge-based attention and word embeddings. Comput. Intell. Neurosci. 2019, 1–10 (2019)

    Google Scholar 

  13. Li, Z., Lian, Y., Ma, X., Zhang, X., Li, C.: Bio-semantic relation extraction with attention-based external knowledge reinforcement. BMC Bioinform 21, 1–18 (2020)

    Article  Google Scholar 

  14. Martinez-Rodriguez, J.L., Hogan, A., Lopez-Arevalo, I.: Information extraction meets the semantic web: a survey. In: Semantic Web, pp. 1–81 (2020)

    Google Scholar 

  15. Mikolov, T., Grave, É., Bojanowski, P., Puhrsch, C., Joulin, A.: Advances in pre-training distributed word representations. In: Proceedings of LREC (2018)

    Google Scholar 

  16. Miller, G.A., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.J.: Introduction to wordnet: an on-line lexical database. Int. J. Lexicography 3(4), 235–244 (1990)

    Article  Google Scholar 

  17. Mitchell, A., Strassel, S., Huang, S., Zakhary, R.: Ace 2004 Multilingual Training Corpus, p. 1. Linguistic Data Consortium, Philadelphia pp (2005)

    Google Scholar 

  18. Navigli, R., Ponzetto, S.P.: Babelnet: the automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artif. Intell. 193, 217–250 (2012)

    Article  MathSciNet  Google Scholar 

  19. Pawar, S., Palshikar, G.K., Bhattacharyya, P.: Relation extraction: a survey. arXiv preprint arXiv:1712.05191 (2017)

  20. Peters, M.E., et al.: Knowledge enhanced contextual word representations. In: Proceedings of EMNLP-IJCNLP, pp. 43–54 (2019)

    Google Scholar 

  21. Poerner, N., Waltinger, U., Schütze, H.: E-BERT: efficient-yet-effective entity embeddings for BERT. In: EMNLP, pp. 803–818. ACL (2020)

    Google Scholar 

  22. Sewlal, R.: Effectiveness of the web as a competitive intelligence tool. South African J. Inf. Manage. 6(1), 1–16 (2004)

    Google Scholar 

  23. Shi, P., Lin, J.: Simple bert models for relation extraction and semantic role labeling. arXiv preprint arXiv:1904.05255 (2019)

  24. Soares, L.B., FitzGerald, N., Ling, J., Kwiatkowski, T.: Matching the blanks: distributional similarity for relation learning. In: Proceedings of ACL, pp. 2895–2905 (2019)

    Google Scholar 

  25. Wang, R., et al.: K-adapter: Infusing knowledge into pre-trained models with adapters. arXiv preprint arXiv:2002.01808 (2020)

  26. Wei, Q., et al.: Relation extraction from clinical narratives using pre-trained language models. In: AMIA Annual Symposium Proceedings, vol. 2019, p. 1236. American Medical Informatics Association (2019)

    Google Scholar 

  27. Wiegand, M., Roth, B., Lasarcyk, E., Köser, S., Klakow, D.: A gold standard for relation extraction in the food domain. In: Proceedings of LREC (2012)

    Google Scholar 

  28. Wu, S., He, Y.: Enriching pre-trained language model with entity information for relation classification. In: Proceedings of ACM CIKM 2019, pp. 2361–2364 (2019)

    Google Scholar 

  29. Yadav, S., Ramesh, S., Saha, S., Ekbal, A.: Relation extraction from biomedical and clinical text: unified multitask learning framework. IEEE/ACM Trans. Comput. Biol. Bioinform. (2020)

    Google Scholar 

  30. Yamada, I., et al.: Wikipedia2Vec: an efficient toolkit for learning and visualizing the embeddings of words and entities from Wikipedia. In: Proceedings of EMNLP: System Demonstrations, pp. 23–30 (2020)

    Google Scholar 

  31. Yamada, I., Shindo, H., Takeda, H., Takefuji, Y.: Joint learning of the embedding of words and entities for named entity disambiguation. In: Proceedings of The 20th SIGNLL CoNLL, pp. 250–259 (2016)

    Google Scholar 

  32. Yamamoto, A., Miyamura, Y., Nakata, K., Okamoto, M.: Company relation extraction from web news articles for analyzing industry structure. In: 2017 IEEE ICSC, pp. 89–92 (2017)

    Google Scholar 

  33. Yan, C., Fu, X., Wu, W., Lu, S., Wu, J.: Neural network based relation extraction of enterprises in credit risk management. In: 2019 IEEE BigComp, pp. 1–6 (2019)

    Google Scholar 

  34. Ye, W., Li, B., Xie, R., Sheng, Z., Chen, L., Zhang, S.: Exploiting entity BIO tag embeddings and multi-task learning for relation extraction with imbalanced data. In: Proceedings of ACL, pp. 1351–1360 (2019)

    Google Scholar 

  35. Zeng, D., Liu, K., Lai, S., Zhou, G., Zhao, J.: Relation classification via convolutional deep neural network. In: Proceedings of COLING: Technical Papers, pp. 2335–2344. ACL, Dublin City University (2014)

    Google Scholar 

  36. Zhang, Y., Zhong, V., Chen, D., Angeli, G., Manning, C.D.: Position-aware attention and supervised data improve slot filling. In: Proceedings of EMNLP, pp. 35–45. ACL (2017)

    Google Scholar 

  37. Zhao, J., Jin, P., Liu, Y.: Business relations in the web: semantics and a case study. J. Softw. 5(8), 826–833 (2010)

    Article  Google Scholar 

  38. Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of ACL (Volume 2: Short Papers), pp. 207–212. ACL (2016)

    Google Scholar 

  39. Zuo, Z., Loster, M., Krestel, R., Naumann, F.: Uncovering business relationships: Context-sensitive relationship extraction for difficult relationship types. In: Proceedings of LWDA (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Geotrend, Toulouse, France

    Hadjer Khaldi, Amine Abdaoui & EunBee Kang

  2. IRIT-CNRS, Toulouse, France

    Hadjer Khaldi, Farah Benamara & Nathalie Aussenac-Gilles

Authors
  1. Hadjer Khaldi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Farah Benamara
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Amine Abdaoui
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nathalie Aussenac-Gilles
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. EunBee Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hadjer Khaldi .

Editor information

Editors and Affiliations

  1. Conservatoire National des Arts et Métiers, Paris, France

    Elisabeth Métais

  2. University of Derby, Derby, UK

    Farid Meziane

  3. German Research Center for Artificial Intelligence, Saarbrücken, Germany

    Helmut Horacek

  4. University of Hertfordshire, Hatfield, UK

    Epaminondas Kapetanios

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

Khaldi, H., Benamara, F., Abdaoui, A., Aussenac-Gilles, N., Kang, E. (2021). Multilevel Entity-Informed Business Relation Extraction. In: Métais, E., Meziane, F., Horacek, H., Kapetanios, E. (eds) Natural Language Processing and Information Systems. NLDB 2021. Lecture Notes in Computer Science(), vol 12801. Springer, Cham. https://doi.org/10.1007/978-3-030-80599-9_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-80599-9_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-80598-2

  • Online ISBN: 978-3-030-80599-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation