Spurious Correlations in Cross-Topic Argument Mining
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Forlagets udgivne version, 1,55 MB, PDF-dokument
Recent work in cross-topic argument mining attempts to learn models that generalise across topics rather than merely relying on within-topic spurious correlations. We examine the effectiveness of this approach by analysing the output of single-task and multi-task models for cross-topic argument mining, through a combination of linear approximations of their decision boundaries, manual feature grouping, challenge examples, and ablations across the input vocabulary. Surprisingly, we show that cross-topic models still rely mostly on spurious correlations and only generalise within closely related topics, e.g., a model trained only on closed-class words and a few common open-class words outperforms a state-of-the-art cross-topic model on distant target topics.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2021 |
Sider | 263-277 |
DOI | |
Status | Udgivet - 2021 |
Begivenhed | Tenth Joint Conference on Lexical and Computational Semantics - SEM 2021 - Online Varighed: 5 aug. 2021 → 6 aug. 2021 |
Konference
Konference | Tenth Joint Conference on Lexical and Computational Semantics - SEM 2021 |
---|---|
By | Online |
Periode | 05/08/2021 → 06/08/2021 |
ID: 300082790