CoSPLADE:面向对话式信息检索的SPLADE情境化方法
CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval
AI总结:
本文提出CoSPLADE,利用CANARD数据集以轻量级学习方式训练基于SPLADE的第一阶段对话检索排序器,并结合T5Mono第二阶段排序器,在TREC CAsT 2020和2021上取得有竞争力的效果。
摘要:
对话式搜索是一项困难的任务,因为它不仅需要基于当前用户查询,还需要基于完整的对话历史来检索文档。以往的大多数方法都专注于依赖查询重构的多阶段排序方法,而查询重构是一个关键的中间步骤,可能导致次优的检索效果。其他方法尝试使用完全神经化的第一阶段检索器,但要么是零样本的,要么依赖于基于带有伪标签的数据集进行完整的学习排序。在这项工作中,我们利用CANARD数据集,提出了一种创新的轻量级学习技术,用于训练基于SPLADE的第一阶段排序器。通过依赖SPLADE稀疏表示,我们表明,当与基于T5Mono的第二阶段排序器结合时,在TREC CAsT 2020和2021评测任务上取得了具有竞争力的结果。
英文摘要:
Conversational search is a difficult task as it aims at retrieving documents based not only on the current user query but also on the full conversation history. Most of the previous methods have focused on a multi-stage ranking approach relying on query reformulation, a critical intermediate step that might lead to a sub-optimal retrieval. Other approaches have tried to use a fully neural IR first-stage, but are either zero-shot or rely on full learning-to-rank based on a dataset with pseudo-labels. In this work, leveraging the CANARD dataset, we propose an innovative lightweight learning technique to train a first-stage ranker based on SPLADE. By relying on SPLADE sparse representations, we show that, when combined with a second-stage ranker based on T5Mono, the results are competitive on the TREC CAsT 2020 and 2021 tracks.
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。