Argument Mining between NLP and Social Sciences
Argument Mining workshop @COLING2022 (hybrid): scholarships for online attendance! Check out details at https://argmining-org.github.io/2022/
Argument Mining is a highly interdisciplinary field in Natural Language Processing. Given a linguistic unit (a speech, an essay, forum post, or a tweet), its goal is to determine what is the position adopted by the author/speaker on a certain topic/issue (e.g., whether or not vaccinations should be enforced), and to identify the support, if any, provided by the speaker for its position. In this introductory course we discuss a selection of issues related to Argument Mining, structured along three main coordinates: the core notion of Argument Quality (How do we recognise good arguments?); the modeling challenges related to the automatic extraction of argument structures (multilingualism; evaluation of different modeling architectures); the application potential (computational social science; education).
The course aims to highlight the interdisciplinary aspect of this field, ranging from the collaboration of theory and practice between NLP and social sciences, to approaching different types of linguistic structures (i.e., social media versus parliamentary texts), linguistic analysis of such structures, and the ethical issues involved (i.e., how to use Argument Mining for the social good).
Gabriella Lapesa has studied digital humanities, linguistics, and cognitive science. She is a computational linguist with a strong interest in distributional semantic modeling in an interdisciplinary setting. More specifically, she has worked on the application of corpus-based methods to cognitive modeling (priming and free associations), theoretical linguistics (semantics of morphology), and political science (policy debates in newspapers).
She holds a Ph.D in cognitive science and is currently the leader of an independent research group, E-DELIB (Powering-up E-DELIBeration: towards AI-supported moderation) funded by the German Ministry of Education and Research and based at the Institute for Natural Language Processing at IMS Stuttgart. Her group works at the intersection between NLP (Argument Mining) and social science (Deliberative Theory) to develop methods and tools to support moderation in e-deliberation (the digitally augmented version of direct democracy).
Eva Maria Vecchi has studied linguistics and mathematics, and holds a Ph.D. degree in cognitive and neuroscience. Her research interests focus on computational semantics and grounding computational tasks to formal and cognitive theory. More specifically, her interests have focused on the use of statistical approaches to meaning representation to approximate both a speaker’s intuition and the knowledge we have gained through generations of theoretical studies on semantics.
She is currently a postdoctoral researcher at the Institute for Natural Language Processing at IMS Stuttgart, working on the E-DELIB project. Her focus is on the interdisciplinary effort between Argument Mining (NLP) techniques and theories in Social Sciences with the goal of a more collaborative, productive, and ethical endeavor for e-deliberation.
Vecchi, E. M., Falk, N., Jundi, I., and Lapesa, G. (2021). Towards argument mining for social good: A survey. In Proceedings of the 59th Conference of the Association for Computational Linguistics, ACL 2021, pages 1338-1352. Association for Computational Linguistics.
Lawrence, J. and Reed, C. (2019). Argument mining: A survey. Computational Linguistics, 45(4):765–818
Cabrio, E. and Villata, S. (2018). Five years of argument mining: a data-driven analysis. In IJCAI
Stede, M. and Schneider, J. (2018) Argumentation Mining. Synthesis Lectures on Human Language Technologies, Vol. 11, No. 2 , Pages 1-191
Argument Mining: conceptual building blocks
Stab, C. and Gurevych, I. (2017). Parsing argumentation structures in persuasive essays. Computational Linguistics, 43(3):619–659
Habernal I and Gurevych, I. 2017. Argumentation Mining in User-Generated Web Discourse. Computational Linguistics, 43(1):125–179.
Daxenberger, J., Eger, S., Habernal, I., Stab, C., and Gurevych, I. (2017). What is the essence of a claim? cross-domain claim identification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2055–2066, Copenhagen, Denmark. Association for Computational Linguistics
Wachsmuth, H. and Werner, T. (2020). Intrinsic quality assessment of arguments. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6739–6745, Barcelona, Spain (Online). International Committee on Computational Linguistics
Wachsmuth, H., Naderi, N., Hou, Y., Bilu, Y., Prabhakaran, V., Thijm, T. A., Hirst, G., and Stein, B. (2017b). Computational argumentation quality assessment in natural language. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 176–187, Valencia, Spain. Association for Computational Linguistics
Skitalinskaya, G., Klaff, J., and Wachsmuth, H. (2021). Learning from revisions: Quality assessment of claims in argumentation at scale. CoRR, abs/2101.10250
The social science perspective: Deliberative Quality
Spada, P. and Vreeland, J. R. (2013). Who moderates the moderators? The effect of non-neutral moderators in deliberative decision making. Journal of Public Deliberation, 9(2,3)
Spada, P., Klein, M., Calabretta, R., Iandoli, L., and Quinto, I. (2015). A first step toward scaling-up deliberation: Optimizing large group e-deliberation using argument maps. In American Political Science Association (APSA), 110th Annual Meeting. Politics after the Digital Revolution, Washington DC
Gerber, M., Bächtiger, A., Shikano, S., Reber, S., and Rohr, S. (2016). Deliberative abilities and influence in a transnational deliberative poll (Europolis). British Journal of Political Science, 48(4):1093–1118
Eger, S., Daxenberger, J., Stab, C., and Gurevych, I. (2019). Cross-lingual argumentation mining: Machine translation (and a bit of projection) is all you need! In Proceedings of the 27th International Conference on Computational Linguistics, pages 831–844
Toledo-Ronen, O., Orbach, M., Bilu, Y., Spector, A., and Slonim, N. (2020). Multilingual argument mining: Datasets and analysis. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 303–317, Online. Association for Computational Linguistics
Spliethöver, M. and Wachsmuth, H. (2020). Argument from old man’s view: Assessing social bias in argumentation. In Proceedings of the 7th Workshop on Argument Mining, pages 76–87, Online. Association for Computational Linguistics