Simulating Bandit Learning from User Feedback for Extractive Question Answering
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reducing data annotation. We show that systems initially trained on few examples can dramatically improve given feedback from users on model-predicted answers, and that one can use existing datasets to deploy systems in new domains without any annotation effort, but instead improving the system on-the-fly via user feedback.
Code (0)
등록된 구현이 없습니다.
Tasks
Extractive Question-AnsweringQuestion AnsweringSimilar Papers 제목 키워드 기반
Simulating Bandit Learning from User Feedback for Extractive Question Answering
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning …
Extractive Question-AnsweringQuestion AnsweringMulti-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast the problem as a stochastic decision-makin…
Decision MakingExtractive Question-AnsweringQuestion AnsweringTest-time AdaptationContinually Improving Extractive QA via Human Feedback
We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answ…
Domain AdaptationExtractive Question-AnsweringQuestion AnsweringReading Like HER: Human Reading Inspired Extractive Summarization
In this work, we re-examine the problem of extractive text summarization for long documents. We observe that the process of extracting summarization of human can be divided into two stages: 1) a rough reading stage to lo…
Decision MakingExtractive SummarizationExtractive Text SummarizationText SummarizationBanditSum: Extractive Summarization as a Contextual Bandit
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extr…
Extractive SummarizationExtractive Text SummarizationReinforcement Learning