Unsupervised Adaptation of Question Answering Systems via Generative Self-training
BERT-era question answering systems have recently achieved impressive performance on several question-answering (QA) tasks. These systems are based on representations that have been pre-trained on self-supervised tasks such as word masking and sentence entailment, using massive amounts of data. Nevertheless, additional pre-training closer to the end-task, such as training on synthetic QA pairs, has been shown to improve performance. While recent work has considered augmenting labelled data and leveraging large unlabelled datasets to generate synthetic QA data, directly adapting to target data has received little attention. In this paper we investigate the iterative generation of synthetic QA pairs as a way to realize unsupervised self adaptation. Motivated by the success of the roundtrip consistency method for filtering generated QA pairs, we present iterative generalizations of the approach, which maximize an approximation of a lower bound on the probability of the adaptation data. By adapting on synthetic QA pairs generated on the target data, our method is able to improve QA systems significantly, using an order of magnitude less synthetic data and training computation than existing augmentation approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSentenceSimilar Papers 제목 키워드 기반
Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection
Answering questions is a primary goal of many conversational systems or search products. While most current systems have focused on answering questions against structured databases or curated knowledge graphs, on-line co…
Domain AdaptationKnowledge GraphsQuestion AnsweringSelf-Supervised Learning+1Unsupervised Domain Adaptation on Question-Answering System with Conversation Data
Machine reading comprehension (MRC) is a task for question answering that finds answers to questions from documents of knowledge. Most studies on the domain adaptation of MRC require documents describing knowledge of the…
Domain AdaptationMachine Reading ComprehensionQuestion AnsweringReading Comprehension+1Semi-Supervised QA with Generative Domain-Adaptive Nets
We study the problem of semi-supervised question answering----utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework, the Generative Domain-Adaptive Nets. In…
Domain AdaptationQuestion Answeringreinforcement-learningReinforcement Learning+1Domain Adaptation for Question Answering via Question Classification
Question answering (QA) has demonstrated impressive progress in answering questions from customized domains. Nevertheless, domain adaptation remains one of the most elusive challenges for QA systems, especially when QA s…
Domain AdaptationGeneral ClassificationQuestion AnsweringZero-shot Generalization in Dialog State Tracking through Generative Question Answering
Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs. In real-world settings with constantly changing services, DST syste…
dialog state trackingDomain AdaptationGenerative Question AnsweringLanguage Modeling+4