Learning by Asking Questions
We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task. LBA differs from standard VQA training in that most questions are not observed during training time, and the learner must ask questions it wants answers to. Thus, LBA more closely mimics natural learning and has the potential to be more data-efficient than the traditional VQA setting. We present a model that performs LBA on the CLEVR dataset, and show that it automatically discovers an easy-to-hard curriculum when learning interactively from an oracle. Our LBA generated data consistently matches or outperforms the CLEVR train data and is more sample efficient. We also show that our model asks questions that generalize to state-of-the-art VQA models and to novel test time distributions.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
Learning through Dialogue Interactions by Asking Questions
A good dialogue agent should have the ability to interact with users by both responding to questions and by asking questions, and importantly to learn from both types of interaction. In this work, we explore this directi…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Simulating and Modeling the Risk of Conversational Search
In conversational search, agents can interact with users by asking clarifying questions to increase their chance to find better results. Many recent works and shared tasks in both NLP and IR communities have focused on i…
Conversational SearchInterpreting Models by Allowing to Ask
Questions convey information about the questioner, namely what one does not know. In this paper, we propose a novel approach to allow a learning agent to ask what it considers as tricky to predict, in the course of produ…
ColorizationLearning to Ask for Conversational Machine Learning
Natural language has recently been explored as a new medium of supervision for training machine learning models. Here, we explore learning classification tasks using language in a conversational setting {--} where the au…
BIG-bench Machine LearningReinforcement LearningWhat Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis
Duplicate Question Identification (DQI) improves the processing efficiency and accuracy of large-scale community question answering and automatic QA system. The purpose of DQI task is to identify whether the paired quest…
Community Question AnsweringNatural Language InferenceParaphrase IdentificationQuestion Answering+1