Sentence-aware Contrastive Learning for Open-Domain Passage Retrieval
Wu Hong, Zhuosheng Zhang, Jin‐Yuan Wang, Hai Zhao
2022Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)18 citationsDOIOpen Access PDF
Abstract
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. Specifically, under our observation that a passage can be organized by multiple semantically different sentences, modeling such a passage as a unified dense vector is not optimal.
Topics & Concepts
Computer scienceGranularitySentenceBenchmark (surveying)Artificial intelligenceFocus (optics)Representation (politics)Sampling (signal processing)Domain (mathematical analysis)Natural language processingMachine learningComputer visionLawPoliticsFilter (signal processing)Operating systemOpticsMathematical analysisPhysicsPolitical scienceGeographyMathematicsGeodesyTopic ModelingMultimodal Machine Learning ApplicationsNatural Language Processing Techniques