Sentence-aware Contrastive Learning for Open-Domain Passage Retrieval
This work addresses a specific bottleneck in dense retrieval for researchers, but it is incremental as it builds on existing contrastive learning methods.
The paper tackled the problem of internal representation conflicts in open-domain passage retrieval by proposing a sentence-aware contrastive learning model with in-passage negative sampling, achieving improved performance on benchmark datasets, especially where conflicts are severe.
Training dense passage representations via contrastive learning has been shown effective for Open-Domain Passage Retrieval (ODPR). Existing studies focus on further optimizing by improving negative sampling strategy or extra pretraining. However, these studies keep unknown in capturing passage with internal representation conflicts from improper modeling granularity. This work thus presents a refined model on the basis of a smaller granularity, contextual sentences, to alleviate the concerned conflicts. In detail, we introduce an in-passage negative sampling strategy to encourage a diverse generation of sentence representations within the same passage. Experiments on three benchmark datasets verify the efficacy of our method, especially on datasets where conflicts are severe. Extensive experiments further present good transferability of our method across datasets.