arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.07679cs.IR
收藏

为第一阶段排序构建集合组合式与否定式表征

Constructing Set-Compositional and Negated Representations for First-Stage Ranking

Antonios Minas Krasakis, Andrew Yates, Evangelos Kanoulas

AI总结:

本研究针对第一阶段排序中独立编码难以处理组合与否定查询的问题,提出基于LSR表征向量运算的零样本方法,包含解耦否定与组合伪术语策略,性能优于微调检索器,并进一步优化了LSR的否定表征能力。

摘要:

集合组合式查询与否定式查询对于表达复杂信息需求至关重要,还能助力发现小众条目,例如关于非欧洲君主的书籍。尽管大语言模型(LLM)近期取得了进展,但第一阶段排序因需要对文档与查询进行独立编码,仍颇具挑战性。这一局限要求构建能封装逻辑运算或否定关系的组合式查询表征,以有效匹配相关文档。在本研究的第一部分,我们探索在零样本设置下,利用基于词汇锚定的学习型稀疏检索(Learned Sparse Retrieval, LSR)表征之间的向量运算来构建此类表征。具体而言,我们提出了仅对查询中被否定部分施加惩罚的“解耦否定(Disentangled Negation)”方法,以及增强LSR处理交集能力的“组合伪术语(Combined Pseudo-Term)”方法。我们发现,该零样本方法具有竞争力,且性能往往优于在组合式数据上微调的检索器,这也凸显了LSR与稠密检索器的某些局限。最后,我们通过允许LSR分配负术语分数、有效惩罚包含被否定术语的文档,解决了部分上述局限,提升了LSR在否定关系方面的表征能力。

英文摘要:

Set compositional and negated queries are crucial for expressing complex information needs and enable the discovery of niche items like Books about non-European monarchs. Despite the recent advances in LLMs, first-stage ranking remains challenging due to the requirement of encoding documents and queries independently from each other. This limitation calls for constructing compositional query representations that encapsulate logical operations or negations, and can be used to match relevant documents effectively. In the first part of this work, we explore constructing such representations in a zero-shot setting using vector operations between lexically grounded Learned Sparse Retrieval (LSR) representations. Specifically, we introduce Disentangled Negation that penalizes only the negated parts of a query, and a Combined Pseudo-Term approach that enhances LSRs ability to handle intersections. We find that our zero-shot approach is competitive and often outperforms retrievers fine-tuned on compositional data, highlighting certain limitations of LSR and Dense Retrievers. Finally, we address some of these limitations and improve LSRs representation power for negation, by allowing them to attribute negative term scores and effectively penalize documents containing the negated terms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑