Open-domain clarification question generation without question examples

10/19/2021
by   Julia White, et al.
0

An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans. However, natural language can be ambiguous or unclear. In cases of uncertainty, humans engage in an interactive process known as repair: asking questions and seeking clarification until their uncertainty is resolved. We propose a framework for building a visually grounded question-asking model capable of producing polar (yes-no) clarification questions to resolve misunderstandings in dialogue. Our model uses an expected information gain objective to derive informative questions from an off-the-shelf image captioner without requiring any supervised question-answer data. We demonstrate our model's ability to pose questions that improve communicative success in a goal-oriented 20 questions game with synthetic and human answerers.

READ FULL TEXT

page 1

page 2

page 7

page 8

research
01/19/2019

Adaptive Artificial Intelligent Q&A Platform

The paper presents an approach to build a question and answer system tha...
research
11/16/2017

Question Asking as Program Generation

A hallmark of human intelligence is the ability to ask rich, creative, a...
research
07/28/2019

What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog

The ability to engage in goal-oriented conversations has allowed humans ...
research
11/09/2019

Interactive Classification by Asking Informative Questions

Natural language systems often rely on a single, potentially ambiguous i...
research
02/04/2022

Interactive Mobile App Navigation with Uncertain or Under-specified Natural Language Commands

We introduce Mobile app Tasks with Iterative Feedback (MoTIF), a new dat...
research
11/21/2017

Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards

Despite significant progress in a variety of vision-and-language problem...
research
12/16/2018

What's to know? Uncertainty as a Guide to Asking Goal-oriented Questions

One of the core challenges in Visual Dialogue problems is asking the que...

Please sign up or login with your details

Forgot password? Click here to reset