Abstract
Current automated lexicography (term definition) techniques cannot include contextual or new term information as a part of their synthesis. Our work proposes a novel data-harvesting scheme that leverages lead paragraphs in Wikipedia to create a dataset used to train automated, context-aware lexicographical models. Furthermore, in order to validate the harvested dataset, we present ConDef, a fine-tuned BART model trained on the harvested data which defines vocabulary terms from a short context. ConDef is shown to be highly accurate in context-dependent lexicography as validated on ROUGE-1 and ROUGE-L measures in an 1000-item withheld test set, achieving scores of \(46.40\%\) and \(43.26\%\) respectively. Furthermore, we demonstrate that ConDef’s synthesis serves as a good proxy for term definitions by achieving a ROUGE-1 measure of \(27.79\%\) directly against gold-standard WordNet definitions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aghajanyan, A., Gupta, A., Shrivastava, A., Chen, X., Zettlemoyer, L., Gupta, S.: Muppet: massive multi-task representations with pre-finetuning. arXiv preprint arXiv:2101.11038 (2021)
Aghajanyan, A., Shrivastava, A., Gupta, A., Goyal, N., Zettlemoyer, L., Gupta, S.: Better fine-tuning by reducing representational collapse. In: Conference Proceedings of ICLR 2021 (2020)
Gage, P.: A new algorithm for data compression. C Users J. 12(2), 23–38 (1994)
Gantar, P., Kosem, I., Krek, S.: Discovering automated lexicography: the case of the slovene lexical database. Int. J. Lexicogr. 29(2), 200–225 (2016)
Gantar, P., Kosem, I., Krek, S.: Discovering automated lexicography: the case of the slovene lexical database. Int. J. Lexicogr. 29, 200–225 (2016)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871–7880. Association for Computational Linguistics (2020)
Li, W., Suzuki, E.: Hybrid context-aware word sense disambiguation in topic modeling based document representation. In: 2020 IEEE International Conference on Data Mining (ICDM), pp. 332–341. IEEE (2020)
Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74–81 (2004)
Loshchilov, I., Hutter, F.: Sgdr: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)
Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Wikipedia Contributors. Wikipedia: Manual of Style (2021). Accessed 1 Oct 2021
Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45. Association for Computational Linguistics (2020)
Xiao, D., et al.: Ernie-gen: an enhanced multi-flow pre-training and fine-tuning framework for natural language generation. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 3997–4003. International Joint Conferences on Artificial Intelligence Organization (2020). Main track
Acknowledgments
The authors would like to thank Mr. Albert Huang for providing computational resources in both exploratory and benchmark training; Mr. Barack Yedidia and Mr. Zen Simone for their time, expertise, and editing; Mr. Wes Chao and Dr. John Feland for general guidance relating to experiment design; and finally Dr. Klint Kanopka for providing us with valuable insight and guidance regarding training and validation strategies.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, H., Sayyah, Z. (2022). ConDef: Automated Context-Aware Lexicography Using Large Online Encyclopedias. In: Arai, K. (eds) Intelligent Computing. SAI 2022. Lecture Notes in Networks and Systems, vol 507. Springer, Cham. https://doi.org/10.1007/978-3-031-10464-0_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-10464-0_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10463-3
Online ISBN: 978-3-031-10464-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)