通过融合多级个性化检索结果，解决对话搜索中的过度个性化问题。
RALI@TREC iKAT 2024: Achieving Personalization via Retrieval Fusion in Conversational Search
- 用不同个性化程度的查询生成多个排名列表并融合
- 在保持用户偏好同时避免偏离原始查询意图
- 适合需要精准个性化但又怕过度定制的研究者
RALI团队参加了2024年TREC互动知识辅助（iKAT）任务。在个性化对话搜索中，准确捕捉用户复杂的搜索意图，需将上下文信息与用户档案中的关键元素结合到查询重写中。用户档案通常包含大量相关信息，每条都可能补充用户的资讯需求。难以忽略任何一条，但引入过多则可能导致偏离原查询，影响搜索效果，这一现象称为过度个性化。为此，我们提出通过融合不同个性化程度查询生成的排序列表，来应对该挑战。
原文摘要 · Abstract (English)
The Recherche Appliquee en Linguistique Informatique (RALI) team participated in the 2024 TREC Interactive Knowledge Assistance (iKAT) Track. In personalized conversational search, effectively capturing a user's complex search intent requires incorporating both contextual information and key elements from the user profile into query reformulation. The user profile often contains many relevant pieces, and each could potentially complement the user's information needs. It is difficult to disregard any of them, whereas introducing an excessive number of these pieces risks drifting from the original query and hinders search performance. This is a challenge we denote as over-personalization. To address this, we propose different strategies by fusing ranking lists generated from the queries with different levels of personalization.
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。