Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge

04/14/2021
by   Bodhisattwa Prasad Majumder, et al.
0

The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to form a global view and compare it to the given context to ascertain what is missing and what is useful in the context. Inspired by this, we propose a model for clarification question generation where we first identify what is missing by taking a difference between the global and the local view and then train a model to identify what is useful and generate a question about it. Our model outperforms several baselines as judged by both automatic metrics and humans.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/15/2022

K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition

Visual Question Generation (VQG) is a task to generate questions from im...
04/21/2021

Diverse and Specific Clarification Question Generation with Keywords

Product descriptions on e-commerce websites often suffer from missing im...
07/23/2019

Modeling question asking using neural program generation

People ask questions that are far richer, more informative, and more cre...
10/04/2020

Inquisitive Question Generation for High Level Text Comprehension

Inquisitive probing questions come naturally to humans in a variety of s...
05/12/2018

Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information

Inquiry is fundamental to communication, and machines cannot effectively...
04/30/2020

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations

We investigate the problem of generating informative questions in inform...
10/12/2021

Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model

Dialogue agents that interact with humans in situated environments need ...