Towards Multi-Agent Communication-Based Language Learning Towards Multi-Agent Communication-Based Language Learning
Paper summary This article makes the argument for *interactive* language learning, motivated by some nice recent small-domain success. I can certainly agree with the motivation: if language is used in conversation, we should be building models which know how to behave in conversation? The authors develop a standard multi-agent communication paradigm, where two agents learn communicate in a single-round reference game. (No references to e.g. Kirby or any [ILM][1] work, which is in the same space.) Agent `A1` examines a referent `R` and "transmits" a one-hot utterance representation to `A2`, who must successfully identify `R` given the utterance. The one-round conversations are a success when `A2` picks the correct referent `R`. The two agents are jointly trained to maximize this success metric via REINFORCE (policy gradient). **This is mathematically equivalent to [the NVIL model (Mnih and Gregor, 2014)][2]**, an autoencoder with "hard" latent codes which is likewise trained by policy gradient methods. They perform a nice thorough evaluation on both successful and "cheating" models. This will serve as a useful reference point / starting point for people interested in interactive language acquisition. The way clear is forward, I think: let's develop agents in more complex environments, interacting in multi-round conversations, with more complex / longer utterances. [1]: [2]:
Towards Multi-Agent Communication-Based Language Learning
Angeliki Lazaridou and Nghia The Pham and Marco Baroni
arXiv e-Print archive - 2016 via arXiv
Keywords: cs.CL, cs.CV, cs.LG


Your comment:

Short Science allows researchers to publish paper summaries that are voted on and ranked!