Abstract
Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language models (LLMs), excel at capturing semantic correlations within utterance embeddings but fall short in determining the specific causal relationships. To overcome this limitation, we propose the incorporation of i.i.d. noise terms into the conversation process, thereby constructing a structural causal model (SCM). It explores how distinct causal relationships of fitted embeddings can be discerned through independent conditions. To facilitate the implementation of deep learning, we introduce the cogn frameworks to handle unstructured conversation data, and employ an autoencoder architecture to regard the unobservable noise as learnable “implicit causes.” Moreover, we curate a synthetic dataset that includes i.i.d. noise. Through comprehensive experiments, we validate the effectiveness and interpretability of our approach. Our code is available in https://github.com/Zodiark-ch/mater-of-our-EMNLP2023-paper.- Anthology ID:
- 2023.emnlp-main.33
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 494–512
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.33
- DOI:
- 10.18653/v1/2023.emnlp-main.33
- Cite (ACL):
- Hang Chen, Xinyu Yang, Jing Luo, and Wenjing Zhu. 2023. How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 494–512, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning (Chen et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.emnlp-main.33.pdf