Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?
Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?
复制标题
查询扩展能否提高强交叉编码器排序器的泛化能力？
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Michael Bendersky
中科院分区：
文献类型：
--
作者：
Minghan Li;Honglei Zhuang;Kai Hui;Zhen Qin;Jimmy Lin;R. Jagerman;Xuanhui Wang;Michael Bendersky
查询扩展已被广泛用于改善第一阶段检索者的搜索结果，但其对第二阶段交叉编码者排名者的影响仍未被探讨。Weller等人最近的一项工作。[44]显示当前的扩展技术有利于DPR和BM25等较弱的模型，但对MonoT5等较强的排名者不利。在本文中，我们重新检验了这一结论，并提出了以下问题：查询扩展能否提高强交叉编码器排名器的泛化能力？为了回答这个问题，我们首先将流行的查询扩展方法应用于最先进的交叉编码器排序器，并验证了零射性能的恶化。我们在实验中确定了交叉编码者的两个关键步骤：高质量的关键字生成和最小干扰的查询修改。我们表明，通过快速工程并通过融合聚集每个扩展查询的排序结果，可以提高强神经排序器的泛化能力。具体地说，我们首先调用指令跟随语言模型来通过推理链生成关键字。利用自一致性和倒数排序权重，进一步动态组合每个扩展查询的排序结果。在BEIR和TREC深度学习2019/2020上的实验表明，遵循这些步骤的MonoT5和RankT5的nDCG@10分数都得到了提高，这为将查询扩展应用于强跨编码器排名器指明了方向。
Query expansion has been widely used to improve the search results of first-stage retrievers, yet its influence on second-stage, cross-encoder rankers remains under-explored. A recent work of Weller et al. [44] shows that current expansion techniques benefit weaker models such as DPR and BM25 but harm stronger rankers such as MonoT5. In this paper, we re-examine this conclusion and raise the following question: Can query expansion improve generalization of strong cross-encoder rankers? To answer this question, we first apply popular query expansion methods to state-of-the-art cross-encoder rankers and verify the deteriorated zero-shot performance. We identify two vital steps for cross-encoders in the experiment: high-quality keyword generation and minimal-disruptive query modification. We show that it is possible to improve the generalization of a strong neural ranker, by prompt engineering and aggregating the ranking results of each expanded query via fusion. Specifically, we first call an instruction-following language model to generate keywords through a reasoning chain. Leveraging self-consistency and reciprocal rank weighting, we further combine the ranking results of each expanded query dynamically. Experiments on BEIR and TREC Deep Learning 2019/2020 show that the nDCG@10 scores of both MonoT5 and RankT5 following these steps are improved, which points out a direction for applying query expansion to strong cross-encoder rankers.
无需相关标签的精确零样本密集检索
DOI：
10.18653/v1/2023.acl-long.99
发表时间：
2023
期刊：
Association for Computational Linguistics
影响因子：
--
作者：
Gao, Luyu;Ma, Xueguang;Lin, Jimmy;Callan, Jamie
通讯作者：
Callan, Jamie