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 2112.01488cs.IRcs.CL
收藏

ColBERTv2:通过轻量级后期交互实现高效检索

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

Stanford University(斯坦福大学);Georgia Institute of Technology(佐治亚理工学院)

Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, Matei Zaharia

摘要:

神经信息检索(IR)极大地推进了搜索和其他知识密集型语言任务。虽然许多神经IR方法将查询和文档编码为单向量表示,但后期交互模型以每个令牌的粒度生成多向量表示,并将相关性建模分解为可扩展的令牌级计算。这种分解已被证明可以使后期交互更有效,但它将这些模型的空间足迹扩大了一个数量级。在这项工作中,我们介绍了ColBERTv 2,检索器,耦合积极的残差压缩机制与去噪监督策略,同时提高后期交互的质量和空间占用。我们在广泛的基准测试中评估ColBERTv 2,在训练域内外建立最先进的质量,同时将后期交互模型的空间占用减少6- 10 $\times$。

英文摘要:

Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce multi-vector representations at the granularity of each token and decompose relevance modeling into scalable token-level computations. This decomposition has been shown to make late interaction more effective, but it inflates the space footprint of these models by an order of magnitude. In this work, we introduce ColBERTv2, a retriever that couples an aggressive residual compression mechanism with a denoised supervision strategy to simultaneously improve the quality and space footprint of late interaction. We evaluate ColBERTv2 across a wide range of benchmarks, establishing state-of-the-art quality within and outside the training domain while reducing the space footprint of late interaction models by 6--10$\times$.

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。

↑