Cross-Lingual Fine-Tuning for Dense Retrieval on Non-English Misspellings in the LoCoMo Benchmark

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data for training is often scarcely available. In this paper, rather than using more cross-lingual data for training, we propose to use cross-lingual query generation to augment passage representations with queries in languages other than the original passage language. These augmented representations are used at inference time so that the representation can enco

Research goal: What is the impact of cross-lingual fine-tuning on dense retrieval performance when evaluated on the LoCoMo benchmark with non-English misspellings?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.5/10.