Mining, Assessing, and Improving Arguments in NLP and the Social Sciences

Gabriella Lapesa, Eva Maria Vecchi, Serena Villata, Henning Wachsmuth


Abstract
Computational argumentation is an interdisciplinary research field, connecting Natural Language Processing (NLP) to other disciplines such as the social sciences. The focus of recent research has concentrated on argument quality assessment: what makes an argument good or bad? We present a tutorial which is an updated edition of the EACL 2023 tutorial presented by the same authors. As in the previous version, the tutorial will have a strong interdisciplinary and interactive nature, and will be structured along three main coordinates: (1) the notions of argument quality (AQ) across disciplines (how do we recognize good and bad arguments?), with a particular focus on the interface between Argument Mining (AM) and Deliberation Theory; (2) the modeling of subjectivity (who argues to whom; what are their beliefs?); and (3) the generation of improved arguments (what makes an argument better?). The tutorial will also touch upon a series of topics that are particularly relevant for the LREC-COLING audience (the issue of resource quality for the assessment of AQ; the interdisciplinary application of AM and AQ in a text-as-data approach to Political Science), in line with the developments in NLP (LLMs for AQ assessment), and relevant for the societal applications of AQ assessment (bias and debiasing). We will involve the participants in two annotation studies on the assessment and the improvement of quality.
Anthology ID:
2024.lrec-tutorials.5
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024): Tutorial Summaries
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Roman Klinger, Naozaki Okazaki, Nicoletta Calzolari, Min-Yen Kan
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
26–32
Language:
URL:
https://aclanthology.org/2024.lrec-tutorials.5
DOI:
Bibkey:
Cite (ACL):
Gabriella Lapesa, Eva Maria Vecchi, Serena Villata, and Henning Wachsmuth. 2024. Mining, Assessing, and Improving Arguments in NLP and the Social Sciences. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024): Tutorial Summaries, pages 26–32, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Mining, Assessing, and Improving Arguments in NLP and the Social Sciences (Lapesa et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-tutorials.5.pdf