Interactive Classification by Asking Informative Questions

by   Lili Yu, et al.
Princeton University
cornell university

Natural language systems often rely on a single, potentially ambiguous input to make one final prediction, which may simplify the problem but degrade end user experience. Instead of making predictions with the natural language query only, we ask the user for additional information using a small number of binary and multiple-choice questions in order to better help users accomplish their goals while minimizing their effort. At each turn, our system decides between asking the most informative question or making the final classification prediction. Our approach enables bootstrapping the system using simple crowdsourcing annotations without expensive human-to-human interaction data. Evaluation demonstrates that our method substantially increases classification accuracy, while effectively balancing the number of questions with the improvement to final accuracy.


CLAM: Selective Clarification for Ambiguous Questions with Large Language Models

State-of-the-art language models are often accurate on many question-ans...

Evaluating Mixed-initiative Conversational Search Systems via User Simulation

Clarifying the underlying user information need by asking clarifying que...

Open-domain clarification question generation without question examples

An overarching goal of natural language processing is to enable machines...

e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations

In this paper we present a new dataset and user simulator e-QRAQ (explai...

IQA: Interactive Query Construction in Semantic Question Answering Systems

Semantic Question Answering (SQA) systems automatically interpret user q...

SwipeCut: Interactive Segmentation with Diversified Seed Proposals

Interactive image segmentation algorithms rely on the user to provide an...

Interactive Question Clarification in Dialogue via Reinforcement Learning

Coping with ambiguous questions has been a perennial problem in real-wor...

Please sign up or login with your details

Forgot password? Click here to reset