Open-Domain Conversational Question Answering with Historical Answers
Hung-Chieh Fang Kuo-Han Hung Chao-Wei Huang Yun-Nung Chen National Taiwan University, Taipei, Taiwan Equal contribution.
Abstract
Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate passages from a large corpus and the latter requires better understanding of a question with contexts to predict the answers. This paper proposes ConvADR-QA that leverages historical answers to boost retrieval performance and further achieves better answering performance. Our experiments on the benchmark dataset, OR-QuAC, demonstrate that our model outperforms existing baselines in both extractive and generative reader settings, well justifying the effectiveness of historical answers for open-domain conversational question answering.111The source code is available at https://github.com/MiuLab/ConvADR-QA.
中文速览
在多轮对话式问答（Conversational Question Answering）中，系统不仅要从海量文档里检索相关段落，还要结合上下文理解问题并给出答案，而现有方法大多只把历史问题拼接起来输入模型，忽视了历史答案所携带的关键信息。本文提出 ConvADR-QA，核心思路是在密集检索（dense retrieval）的查询编码器输入中同时加入历史问题和历史答案，让模型获得更直接的上下文信号，再配合知识蒸馏和抽取式/生成式阅读器完成端到端的开放域对话问答。在标准基准数据集 OR-QuAC 上，ConvADR-QA 在检索和答案预测两个阶段均超越所有已有基线，包括使用更复杂图结构建模的方法。这项工作表明，将历史答案作为显式信号引入检索阶段是一种简单而有效的思路，对推动开放域对话问答系统走向真实应用场景具有重要意义。
原文 arXiv:2211.09401;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2211.09401v1