通过多视角分析提升对话中语义与句法融合能力
A Multi-view Discourse Framework for Integrating Semantic and Syntactic Features in Dialog Agents
- 用MCCA编码语句的语义、位置和句法特征
- 通过CCA学习对话轮次间的关系，提升上下文理解
- 在Ubuntu数据集上显著优于现有方法
多轮对话模型旨在利用对话上下文生成类人回复，现有方法常忽略话语间的交互或视所有话语同等重要。本文提出一种面向检索式对话系统的对话感知框架，用于响应选择。模型首先使用多视角典型相关分析（MCCA）对每条话语和回复进行上下文、位置和句法特征编码；随后通过典型相关分析（CCA）在共享子空间中学习捕捉话语与其前后轮次关系的对话标记。该两阶段方法有效整合了语义与句法特征，实现话语层面的理解。在Ubuntu对话语料库上的实验表明，本模型在自动评价指标上取得显著提升，验证了其在响应选择中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。