对话智能体中整合语义与句法特征的多视角语篇框架
A Multi-view Discourse Framework for Integrating Semantic and Syntactic Features in Dialog Agents
AI总结：
针对现有多轮对话模型忽略话语交互或同等对待所有话语的问题，本文提出语篇感知框架，通过MCCA和CCA两步法整合语义与句法特征，在Ubuntu语料库上提升响应选择效果。
摘要：
多轮对话模型旨在利用由之前对话轮次的话语组成的会话上下文，生成类人响应。现有方法常忽略这些话语间的交互，或将所有话语视为同等重要。本文针对检索式对话系统的响应选择，提出一个语篇感知框架。该模型首先通过多视角典型相关分析（MCCA），用上下文、位置和句法特征编码每个话语与响应；然后通过典型相关分析（CCA），在共享子空间学习捕捉话语与其周围轮次关系的语篇标记。这种两步法有效整合语义与句法特征，构建语篇级理解。在Ubuntu对话语料库上的实验表明，该模型在自动评估指标上取得显著提升，突显其在响应选择中的有效性。
英文摘要：
Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of them as equally significant. This paper introduces a discourse-aware framework for response selection in retrieval-based dialogue systems. The proposed model first encodes each utterance and response with contextual, positional, and syntactic features using Multi-view Canonical Correlation Analysis (MCCA). It then learns discourse tokens that capture relationships between an utterance and its surrounding turns in a shared subspace via Canonical Correlation Analysis (CCA). This two-step approach effectively integrates semantic and syntactic features to build discourse-level understanding. Experiments on the Ubuntu Dialogue Corpus demonstrate that our model achieves significant improvements in automatic evaluation metrics, highlighting its effectiveness in response selection.
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。
