用深度典型相关分析提升对话系统对长程语境的理解能力
Enhancing Dialogue Systems with Discourse-Level Understanding Using Deep Canonical Correlation Analysis
- 引入DCCA学习话语级标记，捕捉话语与上下文关系
- 在Ubuntu对话数据集上响应选择准确率显著提升
- 适合研究长对话建模与上下文过滤的学者参考
对话系统的发展需要更具备上下文感知能力的模型，以有效管理长时间交互。为克服现有模型在捕捉和利用长期对话历史方面的局限，我们提出一种新框架，采用深度典型相关分析（DCCA）实现话语级理解。该框架通过学习话语标记，捕获话语与其周围语境之间的关系，从而更好地理解长程依赖。在Ubuntu对话语料库上的实验表明，响应选择性能显著提升，自动评估指标得分改善明显。结果表明，DCCA有助于对话系统过滤无关上下文，保留关键话语信息，实现更精准的响应检索。
原文摘要 · Abstract (English)
The evolution of conversational agents has been driven by the need for more contextually aware systems that can effectively manage dialogue over extended interactions. To address the limitations of existing models in capturing and utilizing long-term conversational history, we propose a novel framework that integrates Deep Canonical Correlation Analysis (DCCA) for discourse-level understanding. This framework learns discourse tokens to capture relationships between utterances and their surrounding context, enabling a better understanding of long-term dependencies. Experiments on the Ubuntu Dialogue Corpus demonstrate significant enhancement in response selection, based on the improved automatic evaluation metric scores. The results highlight the potential of DCCA in improving dialogue systems by allowing them to filter out irrelevant context and retain critical discourse information for more accurate response retrieval.
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。