DEep COgnition Learning for LAnguage GEneration

Informazioni relative al progetto

DECOLLAGE

ID dell’accordo di sovvenzione: 101088763

DOI

10.3030/101088763

Data della firma CE 5 Aprile 2023

Data di avvio 1 Agosto 2023

Data di completamento 31 Luglio 2028

Finanziato da

• European Research Council (ERC)

Costo totale

€ 1 999 595,00

Contributo UE

€ 1 999 595,00

Coordinato da

INSTITUTO DE TELECOMUNICACOES
Portugal

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (29)

The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation

Autori: Patrick Fernandes, Daniel Deutsch, Mara Finkelstein, Parker Riley, André Martins, Graham Neubig, Ankush Garg, Jonathan Clark, Markus Freitag, Orhan Firat
Pubblicato in: Proceedings of the Eighth Conference on Machine Translation, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.WMT-1.100

Modern Hopfield Networks with Continuous-Time Memories

Autori: Saul Santos, António Farinhas, Daniel C McNamee, André FT Martins
Pubblicato in: ICLR Workshop on New Frontiers in Associative Memories, 2025
Editore: OpenReview.net

$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation

Autori: Saul Santos, António Farinhas, Daniel C McNamee, André F. T. Martins
Pubblicato in: International Conference on Machine Learning (ICML'25), 2025
Editore: OpenReview.net

Findings of the Quality Estimation Shared Task at WMT 2024: Are LLMs Closing the Gap in QE?

Autori: Zerva, Chrysoula; Blain, Frédéric; de Souza, José Guilherme Camargo; Kanojia, Diptesh; Deoghare, Sourabh Dattatray; Guerreiro, Nuno Miguel; Attanasio, Giuseppe; Rei, Ricardo; Orasan, Constantin; Negri, Matteo; Turchi, Marco; Chatterjee, Rajen; Bhattacharyya, Pushpak; Freitag, Markus; Martins, André
Pubblicato in: Proceedings of the Ninth Conference on Machine Translation, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.3

Findings of the WMT 2023 Shared Task on Quality Estimation

Autori: Blain, Frederic; Zerva, Chrysoula; Ribeiro, Ricardo; Guerreiro, Nuno M.; Kanojia, Diptesh; C. de Souza, José G.; Silva, Beatriz; Vaz, Tânia; Jingxuan, Yan; Azadi, Fatemeh; Orasan, Constantin; Martins, André
Pubblicato in: Proceedings of the Eighth Conference on Machine Translation, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.WMT-1.52

Sparse and Structured Hopfield Networks

Autori: Saul José Rodrigues Dos Santos, Vlad Niculae, Daniel C Mcnamee, Andre Martins
Pubblicato in: Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43368-43388, 2024, 2024
Editore: Proceedings of Machine Learning Research (PMLR)

Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

Autori: Duarte M. Alves, José Pombal, Nuno M. Guerreiro, Pedro H. Martins, João Alves, Amin Farajian, Ben Peters, Ricardo Rei, Patrick Fernandes, Sweta Agrawal, Pierre Colombo, José G.C. de Souza, André F.T. Martins
Pubblicato in: Conference on Language Modeling (COLM'24, oral), 2024
Editore: OpenReview.net

Can Automatic Metrics Assess High-Quality Translations?

Autori: Sweta Agrawal, António Farinhas, Ricardo Rei, Andre Martins
Pubblicato in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.EMNLP-MAIN.802

Non-Exchangeable Conformal Risk Control

Autori: António Farinhas, Chryssa Zerva, Dennis Ulmer, André F. T. Martins
Pubblicato in: International Conference on Learning Representations (ICLR), 2024
Editore: OpenReview.net

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

Autori: Marcos V Treviso, Nuno M Guerreiro, Sweta Agrawal, Ricardo Rei, José Pombal, Tania Vaz, Helena Wu, Beatriz Silva, Daan Van Stigt, Andre Martins
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.FINDINGS-EMNLP.892

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation

Autori: Gonçalo R. A. Faria, Sweta Agrawal, António Farinhas, Ricardo Rei, José G. C. de Souza, André F. T. Martins
Pubblicato in: Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024
Editore: OpenReview.net

Non-Exchangeable Conformal Language Generation with Nearest Neighbors

Autori: Dennis Ulmer, Chrysoula Zerva, Andre Martins
Pubblicato in: Findings of the Association for Computational Linguistics: EACL 2024, 2024
Editore: Association for Computational Linguistics

How Effective Are State Space Models for Machine Translation?

Autori: Hugo Pitorro, Pavlo Vasylenko, Marcos Treviso, André Martins
Pubblicato in: Proceedings of the Ninth Conference on Machine Translation, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.111

Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation

Autori: Sweta Agrawal, José G. C. De Souza, Ricardo Rei, António Farinhas, Gonçalo Faria, Patrick Fernandes, Nuno M Guerreiro, Andre Martins
Pubblicato in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.EMNLP-MAIN.803

AdaSplash: Adaptive Sparse Flash Attention

Autori: Nuno Gonçalves, Marcos Treviso, André F. T. Martins
Pubblicato in: International Conference on Machine Learning (ICML'25, oral), 2025
Editore: OpenReview.net

Different Speech Translation Models Encode and Translate Speaker Gender Differently

Autori: Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli, Andre Martins, Giuseppe Attanasio
Pubblicato in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-SHORT.78

Analyzing Context Contributions in LLM-based Machine Translation

Autori: Emmanouil Zaranis, Nuno M Guerreiro, Andre Martins
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.FINDINGS-EMNLP.876

Sparse Activations as Conformal Predictors

Autori: Margarida M Campos, João Cálem, Sophia Sklaviadis, Mario A. T. Figueiredo, Andre Martins
Pubblicato in: Volume 258: International Conference on Artificial Intelligence and Statistics, 3-5 May 2025 (AISTATS), 2025
Editore: Proceedings of Machine Learning Research (PLMR)

Did Translation Models Get More Robust Without Anyone Even Noticing?

Autori: Ben Peters, Andre Martins
Pubblicato in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-LONG.122

Scaling up CometKiwi: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task

Autori: Ricardo Rei, Nuno M. Guerreiro, José Pombal, Daan van Stigt, Marcos Treviso, Luisa Coheur, José G. C. de Souza, André Martins
Pubblicato in: Proceedings of the Eighth Conference on Machine Translation, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.WMT-1.73

Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation

Autori: Emmanouil Zaranis, Giuseppe Attanasio, Sweta Agrawal, Andre Martins
Pubblicato in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-LONG.1228

Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning

Autori: Duarte Alves, Nuno Guerreiro, João Alves, José Pombal, Ricardo Rei, José de Souza, Pierre Colombo, Andre Martins
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.FINDINGS-EMNLP.744

Reranking Laws for Language Generation: A Communication-Theoretic Perspective (spotlight paper)

Autori: António Farinhas, Haau-Sing Li, André F. T. Martins
Pubblicato in: Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024
Editore: OpenReview.net

LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks

Autori: Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi, Desmond Elliott, Raquel Fernández, Albert Gatt, Esam Ghaleb, Mario Giulianelli, Michael Hanna, Alexander Koller, Andre Martins, Philipp Mondorf, Vera Neplenbroek, Sandro Pezzelle, Barbara Plank, David Schlangen, Alessandro Suglia, Aditya K Surikuchi, Ece Takmaz, Alberto Testoni
Pubblicato in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-SHORT.20

XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples

Autori: Peiqin Lin, Andre Martins, Hinrich Schuetze
Pubblicato in: Findings of the Association for Computational Linguistics: NAACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-NAACL.221

An Empirical Study of Translation Hypothesis Ensembling with Large Language Models

Autori: António Farinhas, José de Souza, Andre Martins
Pubblicato in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.EMNLP-MAIN.733

Aligning Neural Machine Translation Models: Human Feedback in Training and Inference

Autori: Miguel Ramos, Patrick Fernandes, António Farinhas, Andre Martins
Pubblicato in: Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), 2024
Editore: European Association for Machine Translation

Sparse Modern Hopfield Networks

Autori: André F. T. Martins, Vlad Niculae, Daniel C. McNamee
Pubblicato in: NeurIPS Workshop on Associative Memories \& Hopfield Networks, 2023
Editore: OpenReview.net

mPLM-Sim: Unveiling Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models

Autori: Peiqin Lin, Chengzhi Hu, Zheyu Zhang, André F. T. Martins, Hinrich Schütze
Pubblicato in: Findings of the Association for Computational Linguistics: EACL 2024, 2024
Editore: Association for Computational Linguistics

Peer reviewed articles (6)

CroissantLLM: A Truly Bilingual French-English Language Model

Autori: Faysse, Manuel; Fernandes, Patrick; Guerreiro, Nuno; Loison, Antonio; Alves, Duarte; Corro, Caio; Boizard, Nicolas; Alves, Jaoe; Rei, Ricardo; Martins, Pedro Raphaël; Casademunt, Antoni; Yvon, François; Martins, André; Viaud, Gautier; Hudelot, Céline; Colombo, Pierre
Pubblicato in: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editore: OpenReview.net
DOI: 10.48550/ARXIV.2402.00786

<b>x<scp>comet</scp> </b>: Transparent Machine Translation Evaluation through Fine-grained Error Detection

Autori: Nuno M. Guerreiro, Ricardo Rei, Daan van Stigt, Luisa Coheur, Pierre Colombo, André F. T. Martins
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 12, 2024, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/TACL_A_00683

Conformalizing Machine Translation Evaluation

Autori: Chrysoula Zerva, André F. T. Martins
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 12, 2024, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/TACL_A_00711

Assessing the Role of Context in Chat Translation Evaluation: Is Context Helpful and Under What Conditions?

Autori: Agrawal, Sweta; Farajian, Amin; Fernandes, Patrick; Rei, Ricardo; Martins, André F. T.
Pubblicato in: Transactions of the Association for Computational Linguistics, 2024, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/TACL_A_00700

Conformal Prediction for Natural Language Processing: A Survey

Autori: Margarida Campos, António Farinhas, Chrysoula Zerva, Mário A. T. Figueiredo, André F. T. Martins
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 12, 2024, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/TACL_A_00715

Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation

Autori: Patrick Fernandes, Aman Madaan, Emmy Liu, António Farinhas, Pedro Henrique Martins, Amanda Bertsch, José G. C. de Souza, Shuyan Zhou, Tongshuang Wu, Graham Neubig, André F. T. Martins
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 11, 2023, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/TACL_A_00626

Monographic books (1)

Discrete Latent Structure in Neural Networks

Autori: Vlad Niculae, Caio Corro, Nikita Nangia, Tsvetomila Mihaylova, André F. T. Martins
Pubblicato in: Foundations and Trends® in Signal Processing, Numero 19, 2025, ISSN 1932-8346
Editore: Now Publishers
DOI: 10.1561/2000000134