Emergent Communication with Attention
Not on the map. Why?
Abstract (arXiv)
To develop computational agents that better communicate using their own emergent language, we endow the agents with an ability to focus their attention on particular concepts in the environment. Humans often understand an object or scene as a composite of concepts and those concepts are further mapped onto words. We implement this intuition as cross-modal attention mechanisms in Speaker and Listener agents in a referential game and show attention leads to more compositional and interpretable emergent language. We also demonstrate how attention aids in understanding the learned communication protocol by investigating the attention weights associated with each message symbol and the alignment of attention weights between Speaker and Listener agents. Overall, our results suggest that attention is a promising mechanism for developing more human-like emergent language.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 18 May 2023.
Builds on
31 of 51 references.
References · 31
- 2017Attention Is All You Needcited by 60,361
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2022A ConvNet for the 2020scited by 3,579
- 2016Gaussian Error Linear Units (GELUs)cited by 3,502
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
- 2019Attention is not Explanationcited by 929
- 2019Attention is not not Explanationcited by 636
- 2015Stacked Attention Networks for Image Question Answeringcited by 273
- 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
- 2016Multi-Agent Cooperation and the Emergence of (Natural) Languagecited by 185
19 more
- 2018Compositional Attention Networks for Machine Reasoningcited by 183
- 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 170
- 2020Compositionality and Generalization in Emergent Languagescited by 103
- 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
- 2020Compositional Languages Emerge in a Neural Iterated Learning Modelcited by 75
- 2019On the Pitfalls of Measuring Emergent Communicationcited by 71
- 2019Ease-of-Teaching and Language Structure from Emergent Communicationcited by 65
- 2018How agents see things: On visual representations in an emergent language gamecited by 45
- 2021Emergent Communication of Generalizationscited by 42
- 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
- 2021Compositional Transformers for Scene Generationcited by 24
- 2022On the role of population heterogeneity in emergent communicationcited by 24
- 2019Word-order biases in deep-agent emergent communicationcited by 18
- 2018On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translationcited by 17
- 2019Transcoding compositionally: using attention to find more generalizable solutionscited by 14
- 2020Internal and external pressures on language emergence: least effort, object constancy and frequencycited by 13
- 2021Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communicationcited by 12
- 2022Prophet Attention: Predicting Attention with Future Attention for Image Captioningcited by 10
- 2020Structural Inductive Biases in Emergent Communicationcited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.