Interactive Classification by Asking Informative Questions
arXiv:1911.03598
Abstract
We study the potential for interaction in natural language classification. We add a limited form of interaction for intent classification, where users provide an initial query using natural language, and the system asks for additional information using binary or multi-choice questions. At each turn, our system decides between asking the most informative question or making the final classification prediction.The simplicity of the model allows for bootstrapping of the system without interaction data, instead relying on simple crowdsourcing tasks. We evaluate our approach on two domains, showing the benefit of interaction and the advantage of learning to balance between asking additional questions and making the final prediction.
Accepted at ACL 2020
References in corpus (8)
- A Structured Self-attentive Sentence Embedding
- A Network-based End-to-End Trainable Task-oriented Dialogue System
- Dialog-based Interactive Image Retrieval
- Dialogue Learning With Human-In-The-Loop
- Evaluating Visual Conversational Agents via Cooperative Human-AI Games
- Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog
- Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation
- Adversarial Domain Adaptation for Duplicate Question Detection