How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning

Hang Chen, Xinyu Yang, Jing Luo, Wenjing Zhu

Submission Type: Regular Long Paper

Submission Track: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Submission Track 2: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Keywords: Causal Discrimination, Conversation, Independent Noise, SCM

TL;DR: We induce the i.i.d. noise into embedding to enhance the causal discrimination of models in the case of the affective reasoning task

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 \textit{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.

Submission Number: 116