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

2021/04/14 by Bodhisattwa Prasad Majumder, Majumder, Bodhisattwa Prasad, Sudha Rao +5 · 2 citations
Computer Science · #Computation and Language (cs.CL) #Expert finding and Q&A systems #FOS: Computer and information sciences #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2104.06828

openalex publication_date 2021/04/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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

Cited by

• How²: How to learn from procedural How-to questions
• Referential ambiguity and clarification requests: comparing human and LLM behaviour

Related

• Alexpaca: Learning Factual Clarification Question Generation Without Examples
• Open-domain clarification question generation without question examples
• ClarQ: A large-scale and diverse dataset for Clarification Question Generation
• Answer-based Adversarial Training for Generating Clarification Questions
• CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models