arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.03648cs.IR
收藏

面向方面学习的多层面稠密检索器的可复现性分析与增强

Reproducibility Analysis and Enhancements for Multi-Aspect Dense Retriever with Aspect Learning

Keping Bi, Xiaojie Sun, Jiafeng Guo, Xueqi Cheng

AI总结:

本文针对多层面稠密检索器MADRAL在公开数据上无法复现的问题,提出用CLS替换OTHER、用内容token表示方面等组件改进方案,并通过实验证明其能显著提升检索性能。

摘要:

多层面稠密检索旨在将方面信息(例如品牌和类别)融入双编码器,以促进相关性匹配。作为早期且具有代表性的多层面稠密检索器,MADRAL学习若干额外的方面嵌入,并将显式方面与隐式方面“OTHER”融合以得到最终表示。MADRAL在专有数据上进行了评估,且其代码未发布,这使得在其他数据集上验证其有效性具有挑战性。我们未能在公开的MA-Amazon数据上复现其有效性,这促使我们探究原因并重新审视其组成部分。我们提出了若干组件替代方案进行比较,包括用“CLS”替换“OTHER”,以及用前几个内容token表示方面。通过大量实验,我们确认在方面融合中从头学习“OTHER”是有害的。相比之下,我们提出的变体能够大幅提升检索性能。我们的研究不仅揭示了MADRAL的局限性,还为未来研究更强大的多层面稠密检索模型提供了有价值的见解。代码将发布于:https://github.com/sunxiaojie99/Reproducibility-for-MADRAL。

英文摘要:

Multi-aspect dense retrieval aims to incorporate aspect information (e.g., brand and category) into dual encoders to facilitate relevance matching. As an early and representative multi-aspect dense retriever, MADRAL learns several extra aspect embeddings and fuses the explicit aspects with an implicit aspect "OTHER" for final representation. MADRAL was evaluated on proprietary data and its code was not released, making it challenging to validate its effectiveness on other datasets. We failed to reproduce its effectiveness on the public MA-Amazon data, motivating us to probe the reasons and re-examine its components. We propose several component alternatives for comparisons, including replacing "OTHER" with "CLS" and representing aspects with the first several content tokens. Through extensive experiments, we confirm that learning "OTHER" from scratch in aspect fusion is harmful. In contrast, our proposed variants can greatly enhance the retrieval performance. Our research not only sheds light on the limitations of MADRAL but also provides valuable insights for future studies on more powerful multi-aspect dense retrieval models. Code will be released at: https://github.com/sunxiaojie99/Reproducibility-for-MADRAL.

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。

↑