提出无损分词剪枝方法，让检索模型仅用30%的词元保持原有效果。
Towards Lossless Token Pruning in Late-Interaction Retrieval Models
- 基于可证明的正则化损失设计剪枝策略，确保删去词元不影响检索分数。
- 实验表明在域内和跨域场景下，仅用30%词元即可保持ColBERT性能。
- 适合需要压缩存储且不接受精度下降的高效检索系统开发者。
晚交互神经信息检索模型（如ColBERT）在多个基准测试中展现出良好的效果与效率平衡。然而，它们需为所有文档词元存储大量上下文表示，占用巨大内存。现有工作多采用启发式或基于统计的方法剪除词元，但无法保证删除不影响检索得分。本文提出一种原则性方法，定义如何剪枝词元而不影响文档与查询间的得分。引入三种正则化损失，实现高剪枝率，结合两种剪枝策略。通过域内与跨域实验验证，可在仅使用30%词元的情况下，保持ColBERT的检索性能。
原文摘要 · Abstract (English)
Late interaction neural IR models like ColBERT offer a competitive effectiveness-efficiency trade-off across many benchmarks. However, they require a huge memory space to store the contextual representation for all the document tokens. Some works have proposed using either heuristics or statistical-based techniques to prune tokens from each document. This however doesn't guarantee that the removed tokens have no impact on the retrieval score. Our work uses a principled approach to define how to prune tokens without impacting the score between a document and a query. We introduce three regularization losses, that induce a solution with high pruning ratios, as well as two pruning strategies. We study them experimentally (in and out-domain), showing that we can preserve ColBERT's performance while using only 30\% of the tokens.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。