Can AMR Assist Legal and Logical Reasoning?
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning
Dokumenter
- Can AMR Assist Legal
Forlagets udgivne version, 264 KB, PDF-dokument
Meaning Representation (AMR) has been shown to be useful for many downstream tasks. In this work, we explore the use of AMR for legal and logical reasoning. Specifically, we investigate if AMR can help capture logical relationships on multiple choice question answering (MCQA) tasks. We propose neural architectures that utilize linearised AMR graphs in combination with pre-trained language models. While these models are not able to outperform text-only baselines, they correctly solve different instances than the text models, suggesting complementary abilities. Error analysis further reveals that AMR parsing quality is the most prominent challenge, especially regarding inputs with multiple sentences. We conduct a theoretical analysis of how logical relations are represented in AMR and conclude it might be helpful in some logical statements but not for others.
Originalsprog | Engelsk |
---|---|
Titel | Findings of the Association for Computational Linguistics: EMNLP 2022 |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2022 |
Sider | 1555-1568 |
Status | Udgivet - 2022 |
Begivenhed | 2022 Findings of the Association for Computational Linguistics: EMNLP 2022 - Abu Dhabi, United Arab Emirates Varighed: 7 dec. 2022 → 11 dec. 2022 |
Konference
Konference | 2022 Findings of the Association for Computational Linguistics: EMNLP 2022 |
---|---|
Land | United Arab Emirates |
By | Abu Dhabi |
Periode | 07/12/2022 → 11/12/2022 |
Bibliografisk note
Publisher Copyright:
© 2022 Association for Computational Linguistics.
Links
- https://aclanthology.org/2022.findings-emnlp.112
Forlagets udgivne version
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
ID: 339845185