面向分面示例查询检索的多分面融合方法
Multi-Facet Blending for Faceted Query-by-Example Retrieval
- Graduate School of Artificial Intelligence, POSTECH（浦项科技大学人工智能研究生院）
- Department of Computer Science and Engineering, POSTECH（浦项科技大学计算机科学与工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对分面示例查询缺乏分面级相关性数据的问题，提出 FaBle 模块化分解与重构增强方法，并发布教育考试题 QBE 基准以验证其效果。
AI中文摘要：
随着满足细粒度用户意图的需求不断增长，基于特定分面检索相似文档的分面示例查询（QBE）近来受到关注。然而，由于缺乏分面级相关性数据集，以往方法主要依赖使用引文等基础指标进行文档级比较；这将其应用限制在基于引文的领域，且无法捕捉分面约束的复杂性。本文提出一种多分面融合（FaBle）增强方法，该方法利用模块化特性，通过分解与重构显式合成面向特定分面的训练集。我们自动将文档分解为分面单元，并借助大语言模型（LLM）内在的区分能力生成相关与不相关文档对；随后，通过动态重构这些单元，得到具备分面级相关性信息的文档对。我们的模块化方法无需预定义的分面知识或标签。此外，为证明 FaBle 在基于引文的科学论文检索之外的新领域中的有效性，我们发布了一个面向教育考试题目 QBE 的基准数据集。在 1000 份文档上进行的 FaBle 增强显著助力模型训练，使其能够获得分面条件嵌入。
英文摘要：
With the growing demand to fit fine-grained user intents, faceted query-by-example (QBE), which retrieves similar documents conditioned on specific facets, has gained recent attention. However, prior approaches mainly depend on document-level comparisons using basic indicators like citations due to the lack of facet-level relevance datasets; yet, this limits their use to citation-based domains and fails to capture the intricacies of facet constraints. In this paper, we propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets. We automatically decompose documents into facet units and generate (ir)relevant pairs by leveraging LLMs' intrinsic distinguishing capabilities; then, dynamically recomposing the units leads to facet-wise relevance-informed document pairs. Our modularization eliminates the need for pre-defined facet knowledge or labels. Further, to prove the FaBle's efficacy in a new domain beyond citation-based scientific paper retrieval, we release a benchmark dataset for educational exam item QBE. FaBle augmentation on 1K documents remarkably assists training in obtaining facet conditional embeddings.
