MIMO: 通过单语目标实现多语言信息检索
MIMO: Multilingual Information Retrieval via Monolingual Objectives
AI总结：
提出MIMO两阶段框架，利用教师模型的稳定英语语义空间，通过知识蒸馏和跨语言对比学习联合优化，解决多语言信息检索中语言聚类和嵌入对齐-均匀性权衡问题。
摘要：
多语言信息检索（MLIR）反映了真实的搜索环境，其中查询和相关文档可能以不同语言出现在混合语言语料库中。然而，现有的嵌入模型主要针对多单语检索进行优化，在MLIR设置中其性能通常会下降。此外，直接将传统对比学习应用于MLIR会加剧语言聚类，并暴露跨语言对齐与嵌入均匀性之间的权衡。为了解决这些局限性，我们提出了MIMO：通过单语目标实现多语言信息检索，这是一个两阶段框架，使用来自高性能教师模型的稳定英语语义空间作为锚点。MIMO首先通过知识蒸馏初始化学生模型的跨语言对齐，然后联合优化蒸馏和跨语言对比学习，以提高检索判别力同时保持对齐。大量实验表明，MIMO在各种MLIR和多单语基准测试中始终优于现有的跨语言训练基线。MIMO在与类似或更大参数规模的现成模型相比也保持竞争力。此外，我们的跨语言对齐-均匀性分析阐明了两个损失组件的不同作用，并表明它们的组合在对齐和均匀性之间产生了有利的权衡。
英文摘要：
Multilingual Information Retrieval (MLIR) reflects real-world search environments in which queries and relevant documents may appear in different languages within a mixed-language corpus. However, existing embedding models are primarily optimized for Multi-Monolingual retrieval and their performance often degrades in MLIR settings. Moreover, directly applying conventional contrastive learning to MLIR can exacerbate language clustering and expose a trade-off between cross-lingual alignment and embedding uniformity. To address these limitations, we propose MIMO: Multilingual Information Retrieval via Monolingual Objectives, a two-stage framework that uses a stable English semantic space from a high-performing teacher model as an anchor. MIMO first initializes the student model's cross-lingual alignment through knowledge distillation, and then jointly optimizes distillation and cross-lingual contrastive learning to improve retrieval discrimination while preserving alignment. Extensive experiments show that MIMO consistently outperforms existing cross-lingual training baselines across various MLIR and Multi-Monolingual benchmarks. MIMO also remains competitive with off-the-shelf models of similar or larger parameter scales. Furthermore, our cross-lingual Alignment-Uniformity analysis clarifies the distinct roles of the two loss components and shows that their combination yields a favorable trade-off between alignment and uniformity.
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。
