Abstract
Debate refers to the behavior of humans using certain reasons to explain their views on things or issues, exposing their contradictions, and finally obtaining a common understanding and opinions. In the current era of massive information and misleading culture, we expect that an AI system that realizes fully autonomous debate can promote the development of intelligent debate, help establish more reasonable arguments, and make more informed decisions. Based on artificial intelligence technology, this task uses deep learning-based algorithms to identify the attributes of input debate topics and claims, including support, opposition, and neutrality. In this task, we transform the Argumentative Text Understanding problem into a classification problem, firstly compared roberta-large, macbert-large, nezha-large, and nezha-large-wwm, and finally chose to use nezha-large with the highest accuracy rate, and achieve 90.2% accuracy in the second stage.
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
References
Slonim, N.: Project Debater. In: COMMA, p. 4. (2018)
Rowe, G., Reed, C.: Translating wigmore diagrams. Front. Artif. Intell. Appl. 144, 171 (2006)
Toulmin, S.E.: The Uses of Argument. Cambridge Univ. Press, Cambridge (1958)
Dung, P.M.: On the acceptability of arguments and its fundamental role in nonmonotonic reasoning. logic programming and n-person games. Artif. Intell. 77(2), 321–357 (1995)
Amgoud, L., Cayrol, C.: On the acceptability of arguments in preference-based argumentation. In: Proceedings of the 14th Annual Conference on Uncertainty in Artificial Intelligence (UAI-98), San Francisco, CA, USA (1998)
Amgoud, L., Cayrol, C.: A reasoning model based on the production of acceptable arguments. Ann. Math. Artif. Intell. 34(1), 197–215 (2002)
Amgoud, L., Serrurier, M.: Agents that argue and explain classifications. Auton. Agent. Multi-Agent Syst. 16(2), 187–209 (2008)
Gómez, S.A., Chesnevar, C.I.: Integrating defeasible argumentation with fuzzy art neural networks for pattern classification. J. Comput. Sci. Technol. 4(1), 45–51 (2004)
Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Lample, G., Conneau, A.: Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291 (2019)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. Adv. Neural Inf. Process. Syst. 32 (2019)
Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for chinese natural language processing. arXiv preprint arXiv:2004.13922 (2020)
Wei, J., et al.: Nezha: neural contextualized representation for Chinese language understanding. arXiv preprint arXiv:1909.00204 (2019)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y., Xia, M., Wang, Y. (2021). Task 1 - Argumentative Text Understanding for AI Debater (AIDebater). In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13029. Springer, Cham. https://doi.org/10.1007/978-3-030-88483-3_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-88483-3_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88482-6
Online ISBN: 978-3-030-88483-3
eBook Packages: Computer ScienceComputer Science (R0)
