如何增强话语的因果判别能力：以情感推理为例
How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning
AI总结：
针对对话情感推理中话语因果判别难的问题，提出引入i.i.d.噪声构建结构因果模型，结合自编码器学习隐式原因，并通过合成数据集实验验证了方法的有效性与可解释性。
摘要：
我们对对话中的情感推理（ARC）任务的调查凸显了因果判别方面的挑战。几乎所有现有模型，包括大型语言模型（LLMs），都擅长捕捉话语嵌入中的语义相关性，但在确定具体因果关系方面却有所欠缺。为克服这一局限，我们提出将独立同分布（i.i.d.）噪声项引入对话过程，从而构建一个结构因果模型（SCM）。该模型探讨了如何通过独立条件来辨别拟合嵌入的不同因果关系。为便于深度学习的实现，我们引入了cogn框架来处理非结构化对话数据，并采用自编码器架构将不可观测的噪声视为可学习的“隐式原因”。此外，我们构建了一个包含i.i.d.噪声的合成数据集。通过全面的实验，我们验证了所提方法的有效性和可解释性。我们的代码可在https://github.com/Zodiark-ch/mater-of-our-EMNLP2023-paper获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
