JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources
This work addresses the challenge of creating state-of-the-art Japanese retrievers with constrained resources, which is an incremental improvement over existing multi-vector models.
This paper tackles the problem of suboptimal training methods for multi-vector retrievers in Japanese, a lower-resource language, by systematically improving inference and training settings and introducing a novel checkpoint merging step, resulting in the JaColBERTv2.5 model that achieves an average score of 0.754, significantly outperforming the previous best of 0.720.
Neural Information Retrieval has advanced rapidly in high-resource languages, but progress in lower-resource ones such as Japanese has been hindered by data scarcity, among other challenges. Consequently, multilingual models have dominated Japanese retrieval, despite their computational inefficiencies and inability to capture linguistic nuances. While recent multi-vector monolingual models like JaColBERT have narrowed this gap, they still lag behind multilingual methods in large-scale evaluations. This work addresses the suboptimal training methods of multi-vector retrievers in lower-resource settings, focusing on Japanese. We systematically evaluate and improve key aspects of the inference and training settings of JaColBERT, and more broadly, multi-vector models. We further enhance performance through a novel checkpoint merging step, showcasing it to be an effective way of combining the benefits of fine-tuning with the generalization capabilities of the original checkpoint. Building on our analysis, we introduce a novel training recipe, resulting in the JaColBERTv2.5 model. JaColBERTv2.5, with only 110 million parameters and trained in under 15 hours on 4 A100 GPUs, significantly outperforms all existing methods across all common benchmarks, reaching an average score of 0.754, significantly above the previous best of 0.720. To support future research, we make our final models, intermediate checkpoints and all data used publicly available.