arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.08372cs.CLcs.IR
收藏

面向开放域稠密检索的多视图文档表示学习

Multi-View Document Representation Learning for Open-Domain Dense Retrieval

Beihang University(北京航空航天大学);Microsoft Research Asia(微软亚洲研究院);Microsoft STC Asia(微软亚洲互联网工程院)

Shunyu Zhang, Yaobo Liang, Ming Gong, Daxin Jiang, Nan Duan

摘要:

稠密检索在大规模文档集的第一阶段检索中取得了令人印象深刻的进步,它建立在双编码器架构上,以产生查询和文档的单一向量表示。但是,一个文档通常可以回答来自不同视图的多个潜在查询。因此,文档的单一向量表示很难与多视图查询匹配,并且面临语义不匹配问题。本文提出了一个多视图文档表示学习框架,旨在产生多视图嵌入来表示文档,并强制它们与不同的查询对齐。首先,我们提出了一个简单而有效的方法,通过观众产生多个嵌入。其次,为了防止多视图嵌入崩溃到同一个,我们进一步提出了一个全局-局部损失与退火温度,以鼓励多个观众更好地与不同的潜在查询对齐。实验表明,我们的方法优于最近的作品,并取得了国家的最先进的结果。

英文摘要:

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document can usually answer multiple potential queries from different views. So the single vector representation of a document is hard to match with multi-view queries, and faces a semantic mismatch problem. This paper proposes a multi-view document representation learning framework, aiming to produce multi-view embeddings to represent documents and enforce them to align with different queries. First, we propose a simple yet effective method of generating multiple embeddings through viewers. Second, to prevent multi-view embeddings from collapsing to the same one, we further propose a global-local loss with annealed temperature to encourage the multiple viewers to better align with different potential queries. Experiments show our method outperforms recent works and achieves state-of-the-art results.

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。

↑