AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Zero-Resource Neural Machine Translation with Multi-Agent Communication Game

Yun Chen, Yang Liu, Victor Li

AAAI 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Emergent communication in referential games · 40 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly train the captioner and translator in the communication game rather than use the fixed-captioner TS teacher-student methodZero-resource NMT · IAPR-TC12 De-EnBLEU: 14.1 -> 18.6Improved
Jointly train the captioner and translator in the communication game rather than use the fixed-captioner TS teacher-student methodZero-resource NMT · IAPR-TC12 En-DeBLEU: 9.2 -> 14.2Improved
Jointly train the captioner and translator in the communication game rather than use the fixed-captioner TS teacher-student methodZero-resource NMT · Multi30K De-EnBLEU: 16.4 -> 19.6Improved
Jointly train the captioner and translator in the communication game rather than use the fixed-captioner TS teacher-student methodZero-resource NMT · Multi30K En-DeBLEU: 10.3 -> 16.6Improved
Jointly optimize the captioner along with the translator instead of keeping the captioner fixed (ablation)Zero-resource NMT · IAPR-TC12 De-EnBLEU: 17.6 -> 18.6Improved
Jointly optimize the captioner along with the translator instead of keeping the captioner fixed (ablation)Zero-resource NMT · IAPR-TC12 En-DeBLEU: 11.9 -> 14.2Improved
Jointly optimize the captioner along with the translator instead of keeping the captioner fixed (ablation)Zero-resource NMT · Multi30K De-EnBLEU: 16.0 -> 19.6Improved
Jointly optimize the captioner along with the translator instead of keeping the captioner fixed (ablation)Zero-resource NMT · Multi30K En-DeBLEU: 12.1 -> 16.6Improved
Jointly train rather than keep the captioner fixed (ablation)Image captioner · IAPR-TC12 image-to-GermanBLEU: 10.7 -> 10.5Hurt
Jointly train rather than keep the captioner fixed (ablation)Image captioner · IAPR-TC12 image-to-EnglishBLEU: 18.0 -> 17.3Hurt
Jointly train rather than keep the captioner fixed (ablation)Image captioner · Multi30K image-to-GermanBLEU: 10.9 -> 12.3Improved
Jointly train rather than keep the captioner fixed (ablation)Image captioner · Multi30K image-to-EnglishBLEU: 22.7 -> 21.3Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy