Match-Prompt
Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng
2022Proceedings of the 31st ACM International Conference on Information & Knowledge Management15 citationsDOIOpen Access PDF
Abstract
dialogue, paraphrase identification, and natural language inference. Experimental results on eighteen public datasets show that Match-Prompt can improve multi-task generalization capability of PLMs in text matching and yield better in-domain multi-task, out-of-domain multi-task and new task adaptation performance than multi-task and task-specific models trained by previous fine-tuning paradigm.
Topics & Concepts
Computer scienceMatching (statistics)GeneralizationArtificial intelligenceTask (project management)Natural language processingQuestion answeringRelevance (law)InferenceSemantic matchingIdentification (biology)ParaphraseMachine learningMathematicsManagementBiologyMathematical analysisStatisticsPolitical scienceEconomicsBotanyLawTopic ModelingNatural Language Processing TechniquesData Quality and Management