Abstract
Injecting real-world information (typically contained in Knowledge Graphs) and human expertise into an end-to-end training pipeline for Natural Language Processing models is an open challenge. In this preliminary work, we propose to approach the task of Named Entity Recognition, which is traditionally viewed as a Sequence Labeling problem, as a Graph Classification problem, where every word is represented as a node in a graph. This allows to embed contextual information as well as other external knowledge relevant to each token, such as gazetteer mentions, morphological form, and linguistic tags. We experiment with a variety of graph modeling techniques to represent words, their contexts, and external knowledge, and we evaluate our approach on the standard CoNLL-2003 dataset. We obtained promising results when integrating external knowledge through the use of graph representation in comparison to the dominant end-to-end training paradigm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chami, I., Abu-El-Haija, S., Perozzi, B., RĆ©, C., Murphy, K.: Machine Learning on Graphs: A Model and Comprehensive Taxonomy. arxiv:2005.03675 (2021)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: 22nd ACM International Conference on Knowledge Discovery and Data Mining (2016)
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NeurIPS (2017)
Yamada, I., Asai, A., Shindo, H., Takeda, H., Matsumoto, Y.: Luke: deep contextualized entity representations with entity-aware self-attention. In: EMNLP (2020)
Acknowledgments
This work has been partially supported by the French National Research Agency (ANR) within the ASRAEL (ANR-15-CE23-0018) and ANTRACT (ANR-17-CE38-0010) projects, and by the European Unionās Horizon 2020 research and innovation program within the MeMAD (GA 780069) project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Harrando, I., Troncy, R. (2021). Named Entity Recognition as Graph Classification. In: Verborgh, R., et al. The Semantic Web: ESWC 2021 Satellite Events. ESWC 2021. Lecture Notes in Computer Science(), vol 12739. Springer, Cham. https://doi.org/10.1007/978-3-030-80418-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-80418-3_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80417-6
Online ISBN: 978-3-030-80418-3
eBook Packages: Computer ScienceComputer Science (R0)