Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Emergent Communication in a Multi-Modal, Multi-Step Referential Game (1705.10369v4)

Published 29 May 2017 in cs.LG, cs.CL, cs.CV, cs.IT, cs.MA, and math.IT

Abstract: Inspired by previous work on emergent communication in referential games, we propose a novel multi-modal, multi-step referential game, where the sender and receiver have access to distinct modalities of an object, and their information exchange is bidirectional and of arbitrary duration. The multi-modal multi-step setting allows agents to develop an internal communication significantly closer to natural language, in that they share a single set of messages, and that the length of the conversation may vary according to the difficulty of the task. We examine these properties empirically using a dataset consisting of images and textual descriptions of mammals, where the agents are tasked with identifying the correct object. Our experiments indicate that a robust and efficient communication protocol emerges, where gradual information exchange informs better predictions and higher communication bandwidth improves generalization.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Katrina Evtimova (3 papers)
  2. Andrew Drozdov (13 papers)
  3. Douwe Kiela (85 papers)
  4. Kyunghyun Cho (292 papers)
Citations (31)
Github Logo Streamline Icon: https://streamlinehq.com

GitHub