Discursive Circuits: How Do Language Models Understand Discourse Relations?
Authors:
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 32558-32577
Abstract
Yisong Miao, Min-Yen Kan. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- eRST: A Signaled Graph Theory of Discourse Relations and OrganizationComputational Linguistics, 2025
- Towards Faithful Model Explanation in NLP: A SurveyComputational Linguistics, 2024
- Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task DesignTransactions of the Association for Computational Linguistics, 2023
- pNLP-Mixer: an Efficient all-MLP Architecture for Language2023
- Connective Prediction for Implicit Discourse Relation Recognition via Knowledge Distillation2023
- Knowledge Neurons in Pretrained Transformers2022
- Towards Unification of Discourse Annotation Frameworks2022
- RST Signalling Corpus: a corpus of signals of coherence relationsLanguage Resources and Evaluation, 2017
- The GUM corpus: creating multilayer resources in the classroomLanguage Resources and Evaluation, 2016
- Brain correlates of discourse processing: An fMRI investigation of irony and conventional metaphor comprehensionNeuropsychologia, 2006