paper-with-me

홈 › Papers

Unsupervised Adaptation of Question Answering Systems via Generative Self-training

2020-11-01 · EMNLP 2020 11 · Steven Rennie, Etienne Marcheret, Neil Mallinar, David Nahamoo, Vaibhava Goel

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringSentence

Similar Papers 제목 키워드 기반

Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection

2019-11-06 · Alexandre Rochette, Yadollah Yaghoobzadeh, Timothy J. Hazen

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+1

Unsupervised Domain Adaptation on Question-Answering System with Conversation Data

2022-09-01 · SIGDIAL (ACL) 2022 9 · Amalia Adiba, Takeshi Homma, Yasuhiro Sogawa

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+1

Semi-Supervised QA with Generative Domain-Adaptive Nets

2017-02-07 · ACL 2017 7 · Zhilin Yang, Junjie Hu, Ruslan Salakhutdinov, William W. Cohen

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+1

Domain Adaptation for Question Answering via Question Classification

2022-09-12 · COLING 2022 10 · Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang 외

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 Answering

Zero-shot Generalization in Dialog State Tracking through Generative Question Answering

2021-01-20 · EACL 2021 2 · Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu 외

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