How agents see things: On visual representations in an emergent language game
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
There is growing interest in the language developed by agents interacting in emergentcommunication settings.Earlier studies have focused on the agents' symbol usage, rather than on their representation of visual input.In this paper, we consider the referential games of Lazaridou et al. (2017), and investigate the representations the agents develop during their evolving interaction.We find that the agents establish successful communication by inducing visual representations that almost perfectly align with each other, but, surprisingly, do not capture the conceptual properties of the objects depicted in the input images.We conclude that, if we are interested in developing language-like communication systems, we must pay more attention to the visual semantics agents associate to the symbols they use.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Representational similarity analysis-connecting the branches of systems neuroscience
Kriegeskorte, N. (2008) · Frontiers in Systems Neuroscience · doi:10.3389/neuro.06.004.2008 · Cited by 3,355
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153 · cited 2×
“They are also somewhat correlated with the input, which we attribute to the fact that untrained neural networks can already extract relevant image features (Jarrett et al., 2009).”
BackgroundConceptual pacts and lexical choice in conversation.
Brennan, S. E., & Clark, H. H. (1996) · Journal of Experimental Psychology Learning Memory and Cognition · doi:10.1037//0278-7393.22.6.1482 · Cited by 1,457
Multi-Agent Cooperation and the Emergence of (Natural) Language
Lazaridou, A., Peysakhovich, A., & Baroni, M. (2016) · arXiv · doi:10.48550/arxiv.1612.07182 · Cited by 231 · cited 6×
“As we faithfully reproduced the setup of Lazaridou et al. (2017), we refer the reader there for hyper-parameters and training details.”
BackgroundMethodInfluentialSelf-citation
Cited by
What Artificial Neural Networks Can Tell Us about Human Language Acquisition
Warstadt, A., & Bowman, S. R. (2022) · Algebraic Structures in Natural Language · doi:10.1201/9781003205388-2 · Cited by 111
Anti-efficient encoding in emergent communication
Chaabouni, R., Kharitonov, E., Dupoux, E., & Baroni, M. (2019) · arXiv · doi:10.48550/arxiv.1905.12561 · Cited by 85
“As part of this trend, several recent studies analyze the properties of the emergent codes [e.g., Kottur et al., 2017, Bouchacourt and Baroni, 2018, Evtimova et al., 2018, Lowe et al., 2019, Graesser et al., 2019].”
BackgroundSelf-citationKuciński, Ł., Korbak, T., Kołodziej, P., & Miłoś, P. (2021) · arXiv · doi:10.48550/arxiv.2111.06464 · Cited by 23
“It is often measured using dedicated metrics such as topographic similarity (Brighton and Kirby (2006); Lazaridou et al. (2018); Kriegeskorte (2008); Bouchacourt and Baroni (2018)), context independence Bogin et al. (2018), conflict count Kuci ´ nski et al. (2020), or positional disentanglement…”
Method“LazImpa”: Lazy and impatient neural agents learn to communicate efficiently
Rita, M., Chaabouni, R., & Dupoux, E. (2020) · Proceedings of the 24th Conference on Computational Natural Language Learning · doi:10.18653/v1/2020.conll-1.26 · Cited by 17
Inukai, J., Taniguchi, T., Taniguchi, A., & Hagiwara, Y. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1229127 · Cited by 12
Metadata
- Authors
- Bouchacourt, D., & Baroni, M.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 981-985
- OpenAlex
- W2888912391
- Cited by
- 78
- References
- 5
- FWCI
- 134.69
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.