Abstract
Research articles and patents contain information in the form of text. Chemical named entity recognition (ChemNER) refers to the process of extracting chemical named entities from research articles or patents. Chemical information extraction pipelines have ChemNER as its first step. Existing ChemNER methods rely on rule-based, dictionary-based, or feature-engineered based approaches. More recently, deep learning-based approaches have been used to approach ChemNER. Deep-learning based methods utilize pre-trained word embeddings such as word2vec and Glove. Previously, we have used embedded language models (ELMo) with Bi-LSTM-CRF to learn the effect of contextual information for ChemNER. In this paper, we further experiment to learn the impact of using in-domain (large unlabelled corpora of chemical patents) pre-trained ELMo for ChemNER and compare it with ELMo pre-trained on biomedical corpora. We report the results on three benchmark corpora and conclude that in-domain embeddings statistically significantly improve F1-score on patent corpus but do not lead to any performance gains for chemical articles corpora.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K. and Dyer, C. : Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360 (2016)
Akhondi, S.A., et al.: Annotated chemical patent corpus: a gold standard for text mining. PloS one 9(9), e107477 (2014)
Li, J., et al.: BioCreative V CDR task corpus: a resource for chemical disease relation extraction. Database, 1–10 (2016)
Pérez-Pérez, M., et al.: Evaluation of chemical and gene/protein entity recognition systems at BioCreative V. 5: the CEMP and GPRO patents tracks. In: Proceedings of the BioCreative Challenge Evaluation Workshop, vol. 5, pp. 11–18 (2017)
Krallinger, M., et al.: The CHEMDNER corpus of chemicals and drugs and its annotation principles. J. Cheminformatics 7(1), S2 (2015)
Reimers, N., Gurevych, I: Reporting score distributions makes a difference: Performance study of lstm-networks for sequence tagging. arXiv preprint arXiv:1707.09861 (2017)
Ma, X., Hovy, E.: End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF. arXiv preprint arXiv:1603.01354 (2016)
Habibi, M., Weber, L., Neves, M., Wiegandt, D.L., Leser, U.: Deep learning with word embeddings improves biomedical named entity recognition. Bioinformatics 33(14), i37–i48 (2017)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., Dean, J. : Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018)
Zhai, Z., et al.: Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings. arXiv preprint arXiv:1907.02679 (2019)
Dernoncourt, F., Lee, J.Y., Szolovits, P.: NeuroNER: an easy-to-use program for named-entity recognition based on neural networks. arXiv preprint arXiv:1705.05487 (2017)
Luo, L., et al.: An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition. Bioinformatics 34(8), 1381–1388 (2017)
Giorgi, J.M., Bader, G.D.: Transfer learning for biomedical named entity recognition with neural networks. Bioinformatics 34(23), 4087–4094 (2018)
Moen, S.P.F.G.H., Ananiadou, T.S.S.: Distributional semantics resources for biomedical text processing. Proc. Lang. Biol. Med. 39–44 (2013)
Crichton, G., Pyysalo, S., Chiu, B., Korhonen, A.: A neural network multi-task learning approach to biomedical named entity recognition. BMC Bioinf. 18(1), 368 (2017)
Weber, L., Münchmeyer, J., Rocktäschel, T., Habibi, M., Leser, U.: HUNER: improving biomedical NER with pretraining. Bioinformatics 36(1), 295–302 (2020)
Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 1019–1027 (2016)
Awan, Z., Kahlke, T., Ralph, P.J., Kennedy, P.J.: Chemical named entity recognition with deep contextualized neural embeddings. In: 11th International Conference of Knowledge Discovery and Information Retrieval (2019)
Giorgi, J.M., Bader, G.D.: Towards reliable named entity recognition in the biomedical domain. Bioinformatics 36(1), 280–286 (2020)
Leaman, R., Wei, C.H., Lu, Z.: tmChem: a high performance approach for chemical named entity recognition and normalization. J. Cheminformatics 7(S1), S3 (2015)
Hemati, W., and Mehler, A.: LSTMVoter: chemical named entity recognition using a conglomerate of sequence labeling tools. J. Cheminformatics 11(1), 1–7 (2019). https://doi.org/10.1186/s13321-018-0327-2
Corbett, P., Boyle, J.: Chemlistem: chemical named entity recognition using recurrent neural networks. J. Cheminformatics 10(1), 59 (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)
Rocktäschel, T., Weidlich, M., Leser, U.: ChemSpot: a hybrid system for chemical named entity recognition. Bioinformatics 28(12), 1633–1640 (2012)
Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data (2001)
Liu, S., Tang, B., Chen, Q., Wang, X.: Drug name recognition: approaches and resources. Information 6(4), 790–810 (2015)
Khare, R., Leaman, R., Lu, Z.: Accessing biomedical literature in the current information landscape. In: Kumar, V.D., Tipney, Hannah Jane (eds.) Biomedical Literature Mining. MMB, vol. 1159, pp. 11–31. Springer, New York (2014). https://doi.org/10.1007/978-1-4939-0709-0_2
Dai, X., Karimi, S., Hachey, B., Paris, C.: Using Similarity Measures to Select Pretraining Data for NER. arXiv preprint arXiv:1904.00585 (2019)
Rebholz-Schuhmann, D., et al.: CALBC silver standard corpus. J. Bioinform. Comput. Biol. 8(01), 163–179 (2010)
Finkel, J.R., Grenager, T., Manning, C.: Incorporating non-local information into information extraction systems by Gibbs sampling. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 363–370. Association for Computational Linguistics, June 2005
Müller, T., Schmid, H., Schütze, H.: Efficient higher-order CRFs for morphological tagging. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 322–332, October 2013
Wei, C.H., Harris, B.R., Kao, H.Y., Lu, Z.: tmVar: a text mining approach for extracting sequence variants in biomedical literature. Bioinformatics 29(11), 1433–1439 (2013)
Usié, A., Alves, R., Solsona, F., Vázquez, M., Valencia, A.: CheNER: chemical named entity recognizer. Bioinformatics 30(7), 1039–1040 (2014)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543, October 2014
Li, F., Zhang, M., Fu, G., Ji, D.: A neural joint model for entity and relation extraction from biomedical text. BMC Bioinform. 18(1), 198 (2017)
Yang, Z., Salakhutdinov, R., Cohen, W.W.: Transfer learning for sequence tagging with hierarchical recurrent networks. arXiv preprint arXiv:1703.06345 (2017)
Zhuang, F., et al.: A Comprehensive Survey on Transfer Learning. arXiv preprint arXiv:1911.02685 (2019)
Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertainty Fuzziness Knowl.-Based Syst. 6(02), 107–116 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Awan, Z., Kahlke, T., Ralph, P.J., Kennedy, P.J. (2020). The Effect of In-Domain Word Embeddings for Chemical Named Entity Recognition. In: Fred, A., Salgado, A., Aveiro, D., Dietz, J., Bernardino, J., Filipe, J. (eds) Knowledge Discovery, Knowledge Engineering and Knowledge Management. IC3K 2019. Communications in Computer and Information Science, vol 1297. Springer, Cham. https://doi.org/10.1007/978-3-030-66196-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-66196-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66195-3
Online ISBN: 978-3-030-66196-0
eBook Packages: Computer ScienceComputer Science (R0)