A Paradigm for Situated and Goal-Driven Language Learning

Abstract

A distinguishing property of human intelligence is the ability to flexibly use language in order to communicate complex ideas with other humans in a variety of contexts. Research in natural language dialogue should focus on designing communicative agents which can integrate themselves into these contexts and productively collaborate with humans. In this abstract, we propose a general situated language learning paradigm which is designed to bring about robust language agents able to cooperate productively with humans.

5 pages, submitted to Machine Intelligence @ NIPS workshop

References in corpus (5)

• Learning Multiagent Communication with Backpropagation
• Dialog-based Language Learning
• Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
• Reasoning About Pragmatics with Neural Listeners and Speakers
• Towards Multi-Agent Communication-Based Language Learning

Cited by in corpus (10)

• Emergence of Compositional Language with Deep Generational Transmission
• Emergence of Communication in an Interactive World with Consistent Speakers
• Emergent Communication in a Multi-Modal, Multi-Step Referential Game
• Are distributional representations ready for the real world? Evaluating word vectors for grounded perceptual meaning
• Building Human-like Communicative Intelligence: A Grounded Perspective
• Towards Socially Intelligent Agents with Mental State Transition and Human Utility
• Winning an Election: On Emergent Strategic Communication in Multi-Agent Networks
• Language (Re)modelling: Towards Embodied Language Understanding
• Multi-Agent Reinforcement Learning as a Computational Tool for Language Evolution Research: Historical Context and Future Challenges
• On Memory Mechanism in Multi-Agent Reinforcement Learning