Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning
Year: 2020
Type: conference-paper
Abstract: We present a method for combining multiagent communication and traditional datadriven approaches to natural language learning, with an end goal of teaching agents to communicate with humans in natural language.Our starting point is a language model that has been trained on generic, not task-specific language data.We then place this model in a multi-agent self-play environment that generates task-specific rewards used to adapt or modulate the model, turning it into a taskconditional language model.We introduce a new way for combining the two types of learning based on the idea of reranking language model samples, and show that this method outperforms others in communicating with humans in a visual referential communication task.Finally, we present a taxonomy of different types of language drift that can occur alongside a set of measures to detect them.
Institutions: Google (United States), Google DeepMind (United Kingdom)
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: DeepMind
OpenAlex ID: W3024893463
