Simulating Bandit Learning from User Feedback for Extractive Question Answering

03/18/2022
by   Ge Gao, et al.
0

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 a small number of 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, but instead improving the system on-the-fly via user feedback.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/21/2023

Continually Improving Extractive QA via Human Feedback

We study continually improving an extractive question answering (QA) sys...
research
11/01/2020

Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning

The interaction of conversational systems with users poses an exciting o...
research
06/07/2023

Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering

Whereas the recent emergence of large language models (LLMs) like ChatGP...
research
04/06/2022

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

Most research on question answering focuses on the pre-deployment stage;...
research
06/20/2020

IQA: Interactive Query Construction in Semantic Question Answering Systems

Semantic Question Answering (SQA) systems automatically interpret user q...
research
12/19/2022

Continual Learning for Instruction Following from Realtime Feedback

We study the problem of continually training an instruction-following ag...
research
02/22/2020

Machine Translation System Selection from Bandit Feedback

Adapting machine translation systems in the real world is a difficult pr...

Please sign up or login with your details

Forgot password? Click here to reset