将对话内容转化为短查询，提升智能搜索的准确性。
Bridging the Gap: From Ad-hoc to Proactive Search in Conversations
- 设计对话转查询模型，解决长文本输入与短查询不匹配问题。
- 在两个数据集上显著提升检索效果，直接使用时效果更优。
- 适合需要高效对话式搜索的系统开发者和研究者。
对话中主动搜索（PSC）旨在通过基于对话上下文主动检索相关信息，减少用户构建明确查询的负担。以往方法直接使用对话上下文作为现成的即兴检索器输入，或在PSC数据上微调这些检索器。然而，即兴检索器预训练于简短、简洁的查询，而PSC输入更长且含噪声，导致输入不匹配，限制了检索质量。尽管在PSC数据上微调有所帮助，但仍受限于这一输入差距。本文提出Conv2Query，一种新的对话转查询框架，通过弥合即兴搜索与PSC之间的输入差异，使即兴检索器适应对话场景。Conv2Query将对话上下文映射为即兴查询，可用于直接输入现成检索器，或用于进一步在PSC数据上微调。在两个PSC数据集上的大量实验表明，Conv2Query显著提升了即兴检索器的表现，无论是否微调均有效。
原文摘要 · Abstract (English)
Proactive search in conversations (PSC) aims to reduce user effort in formulating explicit queries by proactively retrieving useful relevant information given conversational context. Previous work in PSC either directly uses this context as input to off-the-shelf ad-hoc retrievers or further fine-tunes them on PSC data. However, ad-hoc retrievers are pre-trained on short and concise queries, while the PSC input is longer and noisier. This input mismatch between ad-hoc search and PSC limits retrieval quality. While fine-tuning on PSC data helps, its benefits remain constrained by this input gap. In this work, we propose Conv2Query, a novel conversation-to-query framework that adapts ad-hoc retrievers to PSC by bridging the input gap between ad-hoc search and PSC. Conv2Query maps conversational context into ad-hoc queries, which can either be used as input for off-the-shelf ad-hoc retrievers or for further fine-tuning on PSC data. Extensive experiments on two PSC datasets show that Conv2Query significantly improves ad-hoc retrievers' performance, both when used directly and after fine-tuning on PSC.
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。