How does increasing the proportion of mined hard negatives in multilingual dense retrieval training datasets impact Mean

Dense retrieval models using a transformer-based bi-encoder architecture have emerged as an active area of research. In this article, we focus on the task of monolingual retrieval in a variety of typologically diverse languages using such an architecture. Although recent work with multilingual transformers demonstrates that they exhibit strong cross-lingual generalization capabilities, there remain many open research questions, which we tackle here. Our study is organized as a ``best practices'' guide for training multilingual dense retrieval models, broken down into three main scenarios: when a

Research goal: How does increasing the proportion of mined hard negatives in multilingual dense retrieval training datasets impact Mean Reciprocal Rank (MRR) on low-resource language benchmarks compared to standard negative sampling?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.7/10.