Autonomous Linguistic Emergence in neural Networks

Project Information

ALiEN

Grant agreement ID: 101019291

DOI

10.3030/101019291

EC signature date 26 May 2021

Start date 1 January 2022

End date 31 December 2026

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 2 489 541,00

EU contribution

€ 2 489 541,00

Coordinated by

UNIVERSIDAD POMPEU FABRA
Spain

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (11)

Cross-domain image captioning with discriminative finetuning.

Author(s): R. Dessì, M. Bevilacqua, E. Gualdoni, N. Rakotonirina, F. Franzon, M. Baroni
Published in: Proceedings of CVPR 2023 (IEEE/CVF Conference on Computer Vision and Pattern Recognition), 2023, Page(s) 6935-6944
Publisher: Computer Vision Foundation

Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili

Author(s): Jacobs, C., Rakotonirina, N.C., Chimoto, E.A., Bassett, B.A., Kamper, H.
Published in: Proc. INTERSPEECH 2023, 2023
Publisher: ISCA
DOI: 10.21437/interspeech.2023-421

On the Correspondence between Compositionality and Imitation in Emergent Neural Communication

Author(s): E. Cheng, M. Rita, T. Poibeau
Published in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, Page(s) 12432–12447
Publisher: ACL

Referential communication in heterogeneous communities of pre-trained visual deep networks.

Author(s): M. Mahaut, F. Franzon, R. Dessì, M. Baroni
Published in: Proc. of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023), 2023, Page(s) 2619-2621
Publisher: International Foundation for Autonomous Agents and Multiagent Systems

Communication breakdown: On the low mutual intelligibility between human and neural captioning

Author(s): R. Dessì, E. Gualdoni, F. Franzon, G. Boleda, M. Baroni
Published in: Proceedings of EMNLP 2022 (Conference on Empirical Methods in Natural Language Processing), 2022, Page(s) 7998-8007
Publisher: ACL

Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators

Author(s): Matéo Mahaut, Laura Aina, Paula Czarnowska, Momchil Hardalov, Thomas Müller, Lluis Marquez
Published in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, Page(s) 4554-4570
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2024.acl-long.250

Bridging information-theoretic and geometric compression in language models

Author(s): Cheng, Emily; Kervadec, Corentin; Baroni, Marco
Published in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Publisher: Association for Computational Linguistics

MemoryPrompt: A light wrapper to improve context tracking in pre-trained language models

Author(s): Rakotonirina, Nathanael; Baroni, Marco
Published in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024
Publisher: Association for Computational Linguistics

Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Models

Author(s): Richard Antonello, Emily Cheng
Published in: Proceedings of UniReps@NeurIPS 2024, 2024
Publisher: OpenReview/Online

Unnatural language processing: How do language models handle machine-generated prompts?

Author(s): Kervadec, Corentin; Franzon, Francesca; Baroni, Marco
Published in: Findings of EMNLP, 2023
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-emnlp.959

Can discrete information extraction prompts generalize across language models?

Author(s): N. Rakotonirina, R. Dessì, F. Petroni, S. Riedel, M. Baroni
Published in: Proceedings of ICLR 2023 (International Conference on Learning Representations), 2023
Publisher: ICLR