A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
Yilin Niu, Fangkai Jiao, Mantong Zhou, Ting Yao, Jingfang Xu, Minlie Huang
Abstract
Neural models have achieved great success on machine reading comprehension (MRC), many of which typically consist of two components: an evidence extractor and an answer predictor. The former seeks the most relevant information from a reference text, while the latter is to locate or generate answers from the extracted evidence. Despite the importance of evidence labels for training the evidence extractor, they are not cheaply accessible, particularly in many non-extractive MRC tasks such as YES/NO question answering and multi-choice MRC.
Topics & Concepts
ExtractorComputer scienceReading comprehensionArtificial intelligenceReading (process)ComprehensionMachine learningNatural language processingProcess (computing)LinguisticsEngineeringPhilosophyProcess engineeringOperating systemProgramming languageTopic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications