arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.16672cs.IRcs.AIcs.CL
收藏

Jina-ColBERT-v2:一种通用多语言晚期交互检索器

Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever

The University of Texas at Austin(得克萨斯大学奥斯汀分校);Jina AI GmbH(吉纳人工智能有限公司)

Rohan Jha, Bo Wang, Michael Günther, Georgios Mastrapas, Saba Sturua, Isabelle Mohr, Andreas Koukounas, Mohammad Kalim Akram, Nan Wang, Han Xiao

AI总结:

本研究借鉴单向量嵌入模型训练的成熟方法,对ColBERT的架构与训练流程做渐进式改进,推出通用多语言晚期交互检索模型Jina-ColBERT-v2,在多类英文及多语言检索任务上表现优异。

摘要:

多向量稠密模型(如ColBERT)已被证明在信息检索中极具成效。ColBERT的晚期交互打分近似于交叉编码器中所见的查询-文档联合注意力,同时凭借其双编码器架构以及近期在索引和搜索方面的优化,保持了接近传统稠密检索模型的推理效率。在本研究中,我们对ColBERT模型架构和训练流程提出了若干渐进式改进,所采用的方法已在更成熟的单向量嵌入模型训练范式中被验证有效,尤其是那些适用于异构多语言数据、或能在几乎无性能损耗的前提下提升效率的方法。我们的新模型Jina-ColBERT-v2在一系列英文及多语言检索任务上展现出了强劲性能。

英文摘要:

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this work we propose a number of incremental improvements to the ColBERT model architecture and training pipeline, using methods shown to work in the more mature single-vector embedding model training paradigm, particularly those that apply to heterogeneous multilingual data or boost efficiency with little tradeoff. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks.

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。

↑