Elamur Research⌕
☰
home / papers / 2018 / Learning Named Entity Tagger using Domain-Specific Dictionary

Learning Named Entity Tagger using Domain-Specific Dictionary

Summary

Neural NER models no longer need handcrafted features, but they still need large amounts of manually labeled text. In specialized domains, expert annotation is expensive and slow. This paper trains entity taggers using only a domain dictionary and a raw corpus. Labels are produced by exact string matching. To reduce false negatives from limited dictionary coverage, high-quality phrases mined from the corpus (in the spirit of AutoPhrase) are added as entities of "unknown" type.

The authors propose two models that tolerate ambiguous and noisy labels:

  • Fuzzy-LSTM-CRF extends the LSTM-CRF architecture. It maximizes the probability of every label sequence compatible with the supervision under a modified IOBES scheme.
  • AutoNER abandons per-token tagging. It predicts whether neighboring tokens are joined or separated ("Tie or Break") and then assigns a type to each resulting span. The idea is that internal ties survive even when distant supervision gets entity boundaries wrong.

Across three benchmarks, AutoNER outperforms other dictionary-only approaches and comes close to fully supervised systems. This makes NER practical for low-resource domains.

Key points

  • Matching conflicts are resolved by maximizing the number of covered tokens. Each token is then labeled as known-type entity (possibly multi-typed), unknown-type phrase, or non-entity.
  • In Tie or Break, connections that touch unknown-type phrases are labeled Unknown and are ignored during training.
  • Evaluation covers biomedical datasets (BC5CDR, NCBI) and a laptop review dataset for aspect terms, where AutoNER clearly beats Distant-LSTM-CRF.
  • In one learning-curve experiment, AutoNER reached 84.8% F1. A supervised baseline needed at least 300 annotated articles to match it, although with full annotations it still surpassed AutoNER.
  • Ablations show that adding mined phrases and tailoring the dictionary to the corpus both help. Code and data are released at github.com/shangjingbo1226/AutoNER.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Natural language processing

Topics: Named entity recognition · Part-of-speech tagging

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/d18-1230

@inproceedings{shang2018learning,
  title = {{Learning Named Entity Tagger using Domain-Specific Dictionary}},
  author = {Shang, Jingbo and Liu, Liyuan and Gu, Xiaotao and Ren, Xiang and Ren, Teng and Han, Jiawei},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  year = {2018},
  doi = {10.18653/v1/d18-1230},
  url = {https://doi.org/10.18653/v1/d18-1230}
}

References

27 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mark Craven, Johan Kumlien, et al. 1999. Constructing biological knowledge bases by extracting information from text sources. In ISMB, volume 1999, pages 77–86. find
  2. Franck Dernoncourt, Ji Young Lee, Ozlem Uzuner, and Peter Szolovits. 2017. De-identification of patient notes with recurrent neural networks. Journal of the American Medical Informatics Association, 24(3):596–606. find
  3. Oren Etzioni, Michael Cafarella, Doug Downey, Ana-Maria Popescu, Tal Shaked, Stephen Soderland, Daniel S Weld, and Alexander Yates. 2005. Unsupervised named-entity extraction from the web: An experimental study. Artificial intelligence, 165(1):91–134. find
  4. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating non-local information into information extraction systems by gibbs sampling. In Proceedings of the 43rd annual meeting on association for computational linguistics, pages 363–370. Association for Computational Linguistic… find our card
  5. Jason Fries, Sen Wu, Alex Ratner, and Christopher Ré. 2017. Swellshark: A generative model for biomedical named entity recognition without labeled data. arXiv preprint arXiv:1704.06360. — [arXiv:1704.06360](https://arxiv.org/abs/1704.06360) find
  6. Athanasios Giannakopoulos, Claudiu Musat, Andreea Hossmann, and Michael Baeriswyl. 2017. Unsupervised aspect term extraction with b-lstm & crf using automatically labelled datasets. In Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, p… find
  7. Robert Leaman and Graciela Gonzalez. 2008. Banner: an executable survey of advances in biomedical named entity recognition. In Biocomputing 2008, pages 652–663. World Scientific. find
  8. Thomas Lin, Oren Etzioni, et al. 2012. Entity linking at web scale. In Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction, pages 84–88. Association for Computational Linguistics. find
  9. Liyuan Liu, Jingbo Shang, Frank Xu, Xiang Ren, Huan Gui, Jian Peng, and Jiawei Han. 2018. Empower sequence labeling with task-aware neural language model. AAAI. find our card
  10. Xuezhe Ma and Eduard Hovy. 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 (Volume 1: Long Papers), volume 1, pages 1064–1074. find our card
  11. Mike Mintz, Steven Bills, Rion Snow, and Dan Jurafsky. 2009. Distant supervision for relation extraction without labeled data. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2… find
  12. Maria Pontiki, Dimitrios Galanis, John Pavlopoulos, Haris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. Semeval-2014 task 4: Aspect based sentiment analysis. In Proceedings of Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), page 2735. find our card
  13. Daniel Hanisch, Katrin Fundel, Heinz-Theodor Mevis-sen, Ralf Zimmer, and Juliane Fluck. 2005. Prominer: rule-based protein and gene entity recognition. BMC bioinformatics, 6(1):S14. find
  14. Sampo Pyysalo, Filip Ginter, Hans Moen, Tapio Salakoski, and Sophia Ananiadou. 2013. Distributional semantics resources for biomedical text processing. In Proceedings of the 5th International Symposium on Languages in Biology and Medicine, Tokyo, Japan, pages 39–43. find
  15. Wenqi He. 2017. Autoentity: automated entity detection from massive text corpora. M.S. Thesis for Computer Science of University of Illinois at Urbana-Champaign. find
  16. Lev Ratinov and Dan Roth. 2009. Design challenges and misconceptions in named entity recognition. In CoNLL. find our card
  17. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. find
  18. Pavel P Kuksa and Yanjun Qi. 2010. Semi-supervised bio-named entity recognition with word-codebook learning. In Proceedings of the 2010 SIAM International Conference on Data Mining, pages 25–36. SIAM. find
  19. Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural architectures for named entity recognition. In Proceedings of NAACL-HLT, pages 260–270. find
  20. Xiang Ren, Ahmed El-Kishky, Chi Wang, Fangbo Tao, Clare R Voss, and Jiawei Han. 2015. Clustype: Effective entity recognition and typing by relation phrase-based clustering. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 995–1004. ACM. find
  21. Sunil Sahu and Ashish Anand. 2016. Recurrent neural network models for disease name recognition using domain invariant features. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 2216–2225. find
  22. Burr Settles. 2004. Biomedical named entity recognition using conditional random fields and rich feature sets. In Proceedings of the international joint workshop on natural language processing in biomedicine and its applications, pages 104–107. Association for Computational Linguistics. find
  23. Jingbo Shang, Jialu Liu, Meng Jiang, Xiang Ren, Clare R Voss, and Jiawei Han. 2018. Automated phrase mining from massive text corpora. IEEE Transactions on Knowledge and Data Engineering. find
  24. Buzhou Tang, Hongxin Cao, Xiaolong Wang, Qingcai Chen, and Hua Xu. 2014. Evaluating word representation features in biomedical named entity recognition tasks. BioMed research international, 2014. find
  25. Andreas Vlachos and Caroline Gasperin. 2006. Bootstrapping and evaluating named entity recognition in the biomedical domain. In Proceedings of the HLT-NAACL BioNLP Workshop on Linking Natural Language and Biology, pages 138–145. Association for Computational Linguistics. find
  26. Hongning Wang, Yue Lu, and ChengXiang Zhai. 2011. Latent aspect rating analysis without aspect keyword supervision. In Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 618–626. ACM. find
  27. Xuan Wang, Yu Zhang, Xiang Ren, Yuhao Zhang, Marinka Zitnik, Jingbo Shang, Curtis Langlotz, and Jiawei Han. 2018. Cross-type biomedical named entity recognition with deep multi-task learning. arXiv preprint arXiv:1801.09851. — [arXiv:1801.09851](https://arxiv.org/abs/1801.09851) find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/shang-2018-learning-named-entity-tagger-domain/