Open-Retrieval Conversational Question Answering
Open-Retrieval Conversational Question Answering
复制标题
DOI：
10.1145/3397271.3401110
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Chen Qu;Liu Yang;Cen Chen;Minghui Qiu;W. Bruce Croft;Mohit Iyyer
中科院分区：
文献类型：
--
作者：
Chen Qu;Liu Yang;Cen Chen;Minghui Qiu;W. Bruce Croft;Mohit Iyyer
对话式检索是信息检索的最终目标之一。最近的研究方法会话搜索的简化设置的响应排名和会话的问题回答，其中答案是从一个给定的候选集选择或从一个给定的通道中提取。这些简化忽略了检索在会话搜索中的基本作用。为了解决这一限制，我们引入了一个开放式检索对话式问答（ORConvQA）设置，在这里我们学习在提取答案之前从大量集合中检索证据，作为构建功能对话式搜索系统的进一步步骤。我们创建了一个数据集OR-QuAC，以促进对ORConvQA的研究。我们为ORConvQA构建了一个端到端的系统，其中包括一个检索器、一个重新排序器和一个阅读器，这些都是基于Transformers的。我们在OR-QuAC上的大量实验表明，可学习的检索器对ORConvQA至关重要。我们进一步表明，当我们在所有系统组件中启用历史建模时，我们的系统可以做出实质性的改进。此外，我们还表明，重新排序组件通过提供正则化效应来提高模型性能。最后，进行了进一步的深入分析，以提供新的见解ORConvQA。
Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either selected from a given candidate set or extracted from a given passage. These simplifications neglect the fundamental role of retrieval in conversational search. To address this limitation, we introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers, as a further step towards building functional conversational search systems. We create a dataset, OR-QuAC, to facilitate research on ORConvQA. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers. Our extensive experiments on OR-QuAC demonstrate that a learnable retriever is crucial for ORConvQA. We further show that our system can make a substantial improvement when we enable history modeling in all system components. Moreover, we show that the reranker component contributes to the model performance by providing a regularization effect. Finally, further in-depth analyses are performed to provide new insights into ORConvQA.