Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
arXiv:1805.00462
Abstract
Building intelligent agents that can communicate with and learn from humans in natural language is of great value. Supervised language learning is limited by the ability of capturing mainly the statistics of training data, and is hardly adaptive to new scenarios or flexible for acquiring new knowledge without inefficient retraining or catastrophic forgetting. We highlight the perspective that conversational interaction serves as a natural interface both for language learning and for novel knowledge acquisition and propose a joint imitation and reinforcement approach for grounded language learning through an interactive conversational game. The agent trained with this approach is able to actively acquire information by asking questions about novel objects and use the just-learned knowledge in subsequent conversations in a one-shot fashion. Results compared with other methods verified the effectiveness of the proposed approach.
arXiv commentACL 2018
References in corpus (15)
- Playing Atari with Deep Reinforcement Learning
- VQA: Visual Question Answering
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Benchmarking Deep Reinforcement Learning for Continuous Control
- Deep Reinforcement Learning for Dialogue Generation
- Learning Multiagent Communication with Backpropagation
- An Actor-Critic Algorithm for Sequence Prediction
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Third-Person Imitation Learning
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
- Dialog-based Language Learning
- Learning through Dialogue Interactions by Asking Questions
- End-to-end optimization of goal-driven and visually grounded dialogue systems
- Interactive Grounded Language Acquisition and Generalization in a 2D World