Unified Transcription and Translation for Extended Reality

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 .

Risultati finali

First prototype evaluation report

We report on our initial prototypes of Customer Support and Meeting assistants, and their evaluation.

First report on data and resources

Documentation of research efforts and findings within the scope of WP2 (data and resources).

First report on XR models

Documentation of research efforts and findings within the scope of WP3 (multimodal and multilingual pre-trained XR models).

First report on adaptable and context-aware models

Documentation of research efforts and findings within the scope of WP4 (adaptable and context-aware models).

First report on uncertainty-aware, robust and explainable models

Documentation of research efforts and findings within the scope of WP5 (uncertainty-aware, robust and explainable models).

First report on efficient, usable models

Documentation of research efforts and findings within the scope of WP6 (efficient and usable models).

Data management plan

Outlines the resources, tools and protocols to support continuous and compliant management of research data.

First ethics review

Initial review of ethical risks and compliance.

Pubblicazioni

What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability

Autori: Giulianelli, Mario; Baan, Joris; Aziz, Wilker; Fernández, Raquel; Plank, Barbara
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.887

Multilingual Distilwhisper: Efficient Distillation of Multi-Task Speech Models Via Language-Specific Experts

Autori: Ferraz, Thomas Palmeira; Boito, Marcely Zanon; Brun, Caroline; Nikoulina, Vassilina
Pubblicato in: Crossref, 2024
Editore: 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)
DOI: 10.48550/arxiv.2311.01070

Findings of the WMT 2022 Shared Task on Chat Translation

Autori: Ana C Farinha, M. Amin Farajian, Marianna Buchicchio, Patrick Fernandes, José G. C. de Souza, Helena Moniz, André F. T. Martins
Pubblicato in: 2022
Editore: Association for Computational Linguistics

EuroBERT: Scaling Multilingual Encoders for European Languages.

Autori: Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte Miguel Alves, André F. T. Martins, Ayoub Hammal, Caio Corro, CELINE HUDELOT, Emmanuel Malherbe, Etienne Malaboeuf, Fanny Jourdan, Gabriel Hautreux, João Alves, Kevin El Haddad, Manuel Faysse, Maxime Pey
Pubblicato in: COLM 2025, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2503.05500

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

Autori: Emmanouil Zaranis; Giuseppe Attanasio; Sweta Agrawal; Andre Martins
Pubblicato in: ACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-LONG.1228

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

Autori: Ayyoob ImaniGooghari, Peiqin Lin, Amir Hossein Kargaran, Silvia Severini, Masoud Jalili Sabet, Nora Kassner, Chunlan Ma, Helmut Schmid, André Martins, François Yvon, Hinrich Schütze
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.ACL-LONG.61

Multilingual Contextualization of Large Language Models for Document-Level Machine Translation.

Autori: Miguel Moura Ramos, Patrick Fernandes, Sweta Agrawal, André F. T. Martins
Pubblicato in: COLM 2025, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2504.12140

Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention

Autori: Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch
Pubblicato in: 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2410.12462

Chunk-based Nearest Neighbor Machine Translation

Autori: Martins, Pedro Henrique; Marinho, Zita; Martins, André F. T.
Pubblicato in: 2022
Editore: Conference on Empirical Methods for Natural Language Processing, Abu Dhabi, December 2022
DOI: 10.48550/arxiv.2205.12230

Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis

Autori: Hippolyte Gisserot-Boukhlef, Ricardo Rei, Emmanuel Malherbe, Céline Hudelot, Pierre Colombo, Nuno M. Guerreiro
Pubblicato in: WMT 2024, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.127

The Effect of Generalisation on the Inadequacy of the Mode

Autori: Bryan Eikema
Pubblicato in: Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), 2024
Editore: Association for Computational Linguistics

MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue

Autori: Nikita Moghe, Evgeniia Razumovskaia, Liane Guillou, Ivan Vulić, Anna Korhonen, Alexandra Birch
Pubblicato in: 2023
Editore: ACL (Findings)
DOI: 10.48550/arXiv.2212.10455

Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison

Autori: Tsz Kin Lam, Marco Gaido, Sara Papi, Luisa Bentivogli, Barry Haddow
Pubblicato in: NAACL 2025, 2025
Editore: Association for Computational Linguistics

Non-Exchangeable Conformal Language Generation with Nearest Neighbors

Autori: Dennis Ulmer, Chrysoula Zerva, and Andre Martins
Pubblicato in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, Findings, 2024
Editore: Association for Computational Linguistics
DOI: 10.48550/arXiv.2402.00707

mHuBERT-147: A Compact Multilingual HuBERT Model

Autori: Marcely Zanon Boito, Vivek Iyer, Nikolaos Lagos, Laurent Besacier, Ioan Calapodescu
Pubblicato in: Interspeech 2024, 2024
Editore: ISCA
DOI: 10.21437/Interspeech.2024-938

Extrinsic evaluation of machine translation metrics

Autori: Nikita Moghe, Tom Sherborne, Mark Steedman, Alexandra Birch
Pubblicato in: 2023
Editore: ACL (Outstanding paper award)
DOI: 10.48550/arXiv.2212.10297

Efficient Methods for Natural Language Processing: A Survey

Autori: Marcos Treviso, Ji-Ung Lee, Tianchu Ji, Betty van Aken, Qingqing Cao, Manuel R. Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Colin Raffel, Pedro H. Martins, André F. T. Martins, Jessica Zosa Forde, Peter Milder, Edwin Simpson, Noam Slonim, Jess
Pubblicato in: 2023
Editore: Transactions of the ACL, 2023
DOI: 10.48550/arXiv.2209.00099

Towards Effective Disambiguation for Machine Translation with Large Language Models

Autori: Vivek Iyer, Pinzhen Chen, Alexandra Birch
Pubblicato in: 2023
Editore: Conference of Machine Translation
DOI: 10.18653/v1/2023.wmt-1.44

The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights

Autori: Wenhao Zhu, Shujian Huang, Fei Yuan, Cheng Chen, Jiajun Chen, Alexandra Birch
Pubblicato in: 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2405.01345

Prosody in cascade and direct speech-to-text translation: a case study on korean wh-phrases.

Autori: Giulio Zhou, Tsz Kin Lam, Alexandra Birch, and Barry Haddow
Pubblicato in: 2024
Editore: Findings of EACL 2024
DOI: 10.48550/arXiv.2402.00632

On Measuring Context Utilization in Document-Level MT Systems

Autori: Wafaa Mohammed, Vlad Niculae
Pubblicato in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, Findings, 2024
Editore: Association for Computational Linguistics
DOI: 10.48550/arXiv.2402.01404

An Empirical Study of Translation Hypothesis Ensembling with Large Language Models

Autori: Farinhas, António; de Souza, José G. C.; Martins, André F. T.
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-main.733

MaLA-500: Massive Language Adaptation of Large Language Models

Autori: Lin, Peiqin; Ji, Shaoxiong; Tiedemann, Jörg; Martins, André F. T.; Schütze, Hinrich
Pubblicato in: 2024
Editore: arXiv
DOI: 10.48550/arxiv.2401.13303

Disentangling Uncertainty in Machine Translation Evaluation

Autori: Zerva, Chrysoula; Glushkova, Taisiya; Rei, Ricardo; Martins, André F. T.
Pubblicato in: 2022
Editore: Conference on Empirical Methods for Natural Language Processing, Abu Dhabi, December 2022
DOI: 10.48550/arxiv.2204.06546

When natural language is not enough: The limits of in-context learning demonstrations in multilingual reasoning

Autori: Leonardo Ranaldi, Barry Haddow, Alexandra Birch
Pubblicato in: NAACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-NAACL.412

A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models

Autori: Peiqin Lin, André F. T. Martins, Hinrich Schütze
Pubblicato in: NAACL 2025 findings, 2025
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2407.00436

The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics

Autori: Rei, Ricardo; Guerreiro, Nuno M.; Treviso, Marcos; Coheur, Luisa; Lavie, Alon; Martins, André F. T.
Pubblicato in: 2023
Editore: Proceedings of ACL 2023
DOI: 10.48550/arxiv.2305.11806

FINDINGS OF THE IWSLT 2023 EVALUATION CAMPAIGN

Autori: Milind Agarwal, Sweta Agrawal, Antonios Anastasopoulos, Luisa Bentivogli, Ondřej Bojar, Claudia Borg, Marine Carpuat, Roldano Cattoni, Mauro Cettolo, Mingda Chen, William Chen, Khalid Choukri, Alexandra Chronopoulou, Anna Currey, Thierry Declerck, Qianqia
Pubblicato in: 2023
Editore: Proceedings of IWSLT 2023
DOI: 10.18653/v1/2023.iwslt-1.1

HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models

Autori: Wang, Weixuan ; Wu, Minghao ; Haddow, Barry ; Birch, Alexandra
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2505.12300

Rejected Dialects: Biases Against African American Language in Reward Models

Autori: Joel Mire, Zubin Trivadi Aysola, Daniel Chechelnitsky, Nicholas Deas, Chrysoula Zerva, Maarten Sap
Pubblicato in: Findings of the Association for Computational Linguistics: NAACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-NAACL.417

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

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

NAVER LABS Europe Submission to the Instruction Following Track

Autori: Association for Computational Linguistics
Pubblicato in: IWSLT 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.IWSLT-1.17

FINDINGS OF THE IWSLT 2024 EVALUATION CAMPAIGN

Autori: Ibrahim Said Ahmad, Antonios Anastasopoulos, Ondřej Bojar, Claudia Borg, Marine Carpuat, Roldano Cattoni, Mauro Cettolo, William Chen, Qianqian Dong, Marcello Federico, Barry Haddow, Dávid Javorský, Mateusz Krubiński, Tsz Kin Lam, Xutai Ma, Prashant Mathu
Pubblicato in: IWSLT 2025, 2024
Editore: Association for Computational Linguistics

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

Autori: Fernandes, Patrick; Deutsch, Daniel; Finkelstein, Mara; Riley, Parker; Martins, André F. T.; Neubig, Graham; Garg, Ankush; Clark, Jonathan H.; Freitag, Markus; Firat, Orhan
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.wmt-1.100

Asking a Language Model for Diverse Responses

Autori: Sergey Troshin, Irina Saparina, Antske Fokkens, Vlad Niculae
Pubblicato in: EMNLP 2025, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2509.17570

EuroGEST: Investigating gender stereotypes in multilingual language models

Autori: Jacqueline Rowe, Mateusz Klimaszewski, Liane Guillou, Shannon Vallor, Alexandra Birch
Pubblicato in: 2025
Editore: arxiv
DOI: 10.48550/ARXIV.2506.03867

Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning

Autori: Giuseppe Attanasio, Sonal Sannigrahi, Ben Peters, André Filipe Torres Martins
Pubblicato in: 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.IWSLT-1.36

Pitfalls and Outlooks in Using COMET

Autori: Vliem Zouhar, Pinzhen Chen, Tsz Kin Lam, Nikita Moghe, Barry Haddow
Pubblicato in: WMT 2024, 2024
Editore: Association for Computational Linguistics

Compact Speech Translation Models via Discrete Speech Units Pretraining

Autori: Tsz Kin Lam, Alexandra Birch, Barry Haddow
Pubblicato in: IWSLT 2025, 2024
Editore: Association for Computational Linguistics

Overview of the CLEF-2024 Eloquent Lab: Task 2 on HalluciGen

Autori: Luise Dürlich, Evangelia Gogoulou, Liane Guillou, Joakim Nivre, Shorouq Zahra
Pubblicato in: CLEF 2024: Conference and Labs of the Evaluation Forum, 2024
Editore: CEUR

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

Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust

Autori: Markus Freitag, Ricardo Rei, Nitika Mathur, Chi-kiu Lo, Craig Stewart, Eleftherios Avramidis, Tom Kocmi, George Foster, Alon Lavie, André F. T. Martins
Pubblicato in: 2022
Editore: Association for Computational Linguistics

From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLM.

Autori: Ambilduke, Kshitij ; Peters, Ben ; Sannigrahi, Sonal ; Keshwani, Anil ; Lam, Tsz Kin ; Martins, Bruno ; Martins, André F. T. ; Boito, Marcely Zanon
Pubblicato in: Findings of EMNLP 2025, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2503.10620

EuroLLM-9B: Technical Report

Autori: Pedro Henrique Martins, João Alves, Patrick Fernandes, Nuno M. Guerreiro, Ricardo Rei, Amin Farajian, Mateusz Klimaszewski, Duarte M. Alves, José Pombal, Nicolas Boizard, Manuel Faysse, Pierre Colombo, François Yvon, Barry Haddow, José G. C. de Souza, Ale
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2506.04079

Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation

Autori: Lorenzo Lupo, Marco Dinarelli, Laurent Besacier
Pubblicato in: The Fourth Workshop on Insights from Negative Results in NLP, 2023
Editore: Association for Computational Linguistics

What Do Compressed Multilingual Machine Translation Models Forget?

Autori: Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard, Caroline Brun, James Henderson, Laurent Besacier
Pubblicato in: No journal title, 2022
Editore: ACL Anthology
DOI: 10.18653/v1/2022.findings-emnlp.317

Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responses

Autori: Evgenia Ilia, Wilker Aziz
Pubblicato in: 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2412.15683

COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task

Autori: Ricardo Rei, José G. C. de Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, André F. T. Martins
Pubblicato in: 2022
Editore: Association for Computational Linguistics

Findings of the WMT 2023 Shared Task on Quality Estimation

Autori: Frederic Blain, Chrysoula Zerva, Ricardo Rei, Nuno M. Guerreiro, Diptesh Kanojia, José G. C. de Souza, Beatriz Silva, Tânia Vaz, Yan Jingxuan, Fatemeh Azadi, Constantin Orasan, André Martins
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.wmt-1.52

Did translation models get more robust without anyone even noticing?

Autori: Ben Peters, André Martins
Pubblicato in: ACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-LONG.122

Speech-MASSIVE: a multilingual speech dataset for SLU and beyond

Autori: Beomseok Lee, Marco Gaido, Matteo Negri, Ioan Calapodescu, Laurent Besacier
Pubblicato in: Interspeech 2024, 2024
Editore: Interspeech 2024
DOI: 10.48550/ARXIV.2408.03900

Findings of the 2023 conference on machine translation (WMT23): LLMs are here but not quite there yet.

Autori: Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Philipp Koehn, Benjamin Marie, Christof Monz, Makoto Morishita, Kenton Murra
Pubblicato in: 2023
Editore: Proceedings of WMT 2023
DOI: 10.18653/v1/2023.wmt-1.1

Teaching Language Models to Faithfully Express their Uncertainty

Autori: Bryan Eikema, Evgenia Ilia, José G. C. de Souza, Chrysoula Zerva, Wilker Aziz
Pubblicato in: 2025
Editore: arXiv

M-Prometheus: A Suite of Open Multilingual LLM Judges.

Autori: Pombal, José ; Yoon, Dongkeun ; Fernandes, Patrick ; Wu, Ian ; Kim, Seungone ; Rei, Ricardo ; Neubig, Graham ; Martins, André F. T.
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2504.04953

Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation

Autori: Guerreiro, Nuno M.; Voita, Elena; Martins, André F. T.
Pubblicato in: 2022
Editore: ACL Anthology
DOI: 10.18653/V1/2023.EACL-MAIN.75

Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering.

Autori: Patrick Fernandes, Sweta Agrawal, Emmanouil Zaranis, André F.T. Martins, Graham Neubig
Pubblicato in: COLM 2025, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2504.07583

CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task

Autori: Ricardo Rei, Marcos Treviso, Nuno M. Guerreiro, Chrysoula Zerva, Ana C Farinha, Christine Maroti, José G. C. de Souza, Taisiya Glushkova, Duarte Alves, Luisa Coheur, Alon Lavie, André F. T. Martins
Pubblicato in: 2022
Editore: Association for Computational Linguistics

Findings of the WMT24 General Machine Translation Shared Task: The LLM Era Is Here but MT Is Not Solved Yet

Autori: Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Benjamin Marie, Christof Monz, Kenton Murr
Pubblicato in: 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.1

CREST: A Joint Framework for Rationalization and Counterfactual Text Generation

Autori: Treviso, Marcos; Ross, Alexis; Guerreiro, Nuno M.; Martins, André F. T.
Pubblicato in: 2023
Editore: Proceedings of ACL 2023
DOI: 10.48550/arxiv.2305.17075

Self-training Reduces Flicker in Retranslation-based Simultaneous Translation

Autori: Sukanta Sen, Rico Sennrich, Biao Zhang, Barry Haddow
Pubblicato in: ACL, 2023
Editore: Proceedings of EACL 2023

Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection

Autori: Beomseok Lee, Marco Gaido, Ioan Calapodescu, Laurent Besacier, Matteo Negri
Pubblicato in: COLING 2025, 2024
Editore: COLING

Cheating to Identify Hard Problems for Neural Machine Translation

Autori: Proyag Pal, Kenneth Heafield
Pubblicato in: 2023
Editore: EACL (Findings)
DOI: 10.18653/v1/2023.findings-eacl.120

Prompting, Retrieval, Training: An exploration of different approaches for task-oriented dialogue generation

Autori: Pedro Henrique Martins, João Alves, Tânia Vaz, Madalena Gonçalves, Beatriz Silva, Marianna Buchicchio, José GC de Souza, André FT Martins
Pubblicato in: 2023
Editore: European Association for Machine Translation
DOI: 10.18653/v1/2023.sigdial-1.37

Empirical Assessment of kNN-MT for Real-World Translation Scenarios

Autori: Pedro Henrique Martins, João Alves, Tânia Vaz, Madalena Gonçalves, Beatriz Silva, Marianna Buchicchio, José G. C. de Souza, André F. T. Martins
Pubblicato in: 2023
Editore: European Association for Machine Translation

Exploring Enhanced Code-Switched Noising for Pretraining in Neural Machine Translation

Autori: Vivek Iyer, Arturo Oncevay, Alexandra Birch
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-eacl.72

Effects of context on the use of descriptive verbs

Autori: Radina Dobreva, Frank Keller, and Alexandra Birch
Pubblicato in: Proceedings of the Annual Meeting of the Cognitive Science Society, 2024, ISSN 1069-7977
Editore: Cognitive Science Society

No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement

Autori: Klimaszewski, Mateusz ; Andruszkiewicz, Piotr ; Birch, Alexandra
Pubblicato in: 2024
Editore: ACL
DOI: 10.48550/ARXIV.2404.15737

Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation

Autori: Biao Zhang, Barry Haddow, Rico Sennrich
Pubblicato in: ACL Anthology, 2023
Editore: Association for Computational Linguistics

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs

Autori: Sergey Troshin, Wafaa Mohammed, Yan Meng, Christof Monz, Antske Fokkens, Vlad Niculae
Pubblicato in: Second Conference on Language Modeling, 2025, 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2510.01218

LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models

Autori: Hugo Pitorro, Marcos Vinicius Treviso
Pubblicato in: ACL, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-LONG.1194

Improving Context Usage for Translating Bilingual Customer Support Chat with Large Language Models

Autori: Jose Pombal, Sweta Agrawal, André Martins
Pubblicato in: Proceedings of the Ninth Conference on Machine Translation, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.100

ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models

Autori: Thibaut Thonet, Jos Rozen, Laurent Besacier
Pubblicato in: COLING 2025, 2025
Editore: COLING

Can Automatic Metrics Assess High-Quality Translations?

Autori: Sweta Agrawal, António Farinhas, Ricardo Rei, André F.T. Martins
Pubblicato in: EMNLP 2024, 2024
Editore: Association for Computational Linguistics

EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models

Autori: Ji, Shaoxiong ; Li, Zihao ; Paul, Indraneil ; Paavola, Jaakko ; Lin, Peiqin ; Chen, Pinzhen ; O'Brien, Dayyán ; Luo, Hengyu ; Schütze, Hinrich ; Tiedemann, Jörg ; Haddow, Barry
Pubblicato in: 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2409.17892

Robust MT Evaluation with Sentence-level Multilingual Augmentation

Autori: Duarte Alves, Ricardo Rei, Ana C Farinha, José G. C. de Souza, André F. T. Martins
Pubblicato in: 2022
Editore: Association for Computational Linguistics

Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding

Autori: Wafaa Mohammed, Vlad Niculae, Chrysoula Zerva
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2510.06866

The Only Way is Ethics: A Guide to Ethical Research with Large Language Models

Autori: Eddie L. Ungless, Nikolas Vitsakis, Zeerak Talat, James Garforth, Björn Ross, Arno Onken, Atoosa Kasirzadeh, Alexandra Birch
Pubblicato in: COLING '25, 2024
Editore: COLING '25
DOI: 10.48550/ARXIV.2412.16022

Findings of the WMT 2024 Shared Task on Chat Translation

Autori: Wafaa Mohammed, Sweta Agrawal, Amin Farajian, Vera Cabarrão, Bryan Eikema, Ana C Farinha, José G. C. De Souza
Pubblicato in: 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.59

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 GC de Souza, André FT Martins
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.wmt-1.73

Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation

Autori: Nuno M. Guerreiro, Pierre Colombo, Pablo Piantanida, André Martins
Pubblicato in: ACL Anthology, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-long.770

NAVER LABS Europe’s Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track

Autori: Edward Gow-Smith, Alexandre Berard, Marcely Zanon Boito, Ioan Calapodescu
Pubblicato in: ACL Anthology, 2023
Editore: ACL Anthology
DOI: 10.18653/v1/2023.iwslt-1.10

Findings of the WMT 2022 Shared Task on Quality Estimation

Autori: Chrysoula Zerva, Frédéric Blain, Ricardo Rei, Piyawat Lertvittayakumjorn, José G. C. de Souza, Steffen Eger, Diptesh Kanojia, Duarte Alves, Constantin Orăsan, Marina Fomicheva, André F. T. Martins, Lucia Specia
Pubblicato in: Proceedings of the Seventh Conference on Machine Translation (WMT), 2022
Editore: Association for Computational Linguistics

ExpertSteer: Intervening in LLMs through Expert Knowledge

Autori: Wang, Weixuan ; Wu, Minghao ; Haddow, Barry ; Birch, Alexandra
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2505.12313

An Open Dataset and Model for Language Identification

Autori: Laurie Burchell, Alexandra Birch, Nikolay Bogoychev, Kenneth Heafield
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-short.75

Prompting Large Language Model for Machine Translation: A Case Study

Autori: Biao Zhang, Barry Haddow, Alexandra Birch
Pubblicato in: No journal title, 2023
Editore: Arxiy Preprint
DOI: 10.48550/arXiv.2301.07069

PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India

Autori: Ashok Urlan, Pinzhen Chen, Zheng Zhao, Shay Cohen, Manish Shrivastava and Barry Haddow
Pubblicato in: 2023
Editore: Association for Computational Linguistics

Overview of ELOQUENT 2024—Shared Tasks for Evaluating Generative Language Model Quality

Autori: Jussi Karlgren, Luise Dürlich, Evangelia Gogoulou, Liane Guillou, Joakim Nivre, Magnus Sahlgren, Aarne Talman, Shorouq Zahra
Pubblicato in: Lecture Notes in Computer Science, Experimental IR Meets Multilinguality, Multimodality, and Interaction, 2024, ISSN 1611-3349
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-71908-0_3

Code-Switching with Word Senses for Pretraining in Neural Machine Translation

Autori: Vivek Iyer, Edoardo Barba, Alexandra Birch, Jeff Z Pan, Roberto Navigli
Pubblicato in: 2023
Editore: EMNLP (Findings)
DOI: 10.18653/v1/2023.findings-emnlp.859

VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking

Autori: Angelos Nalmpantis, Apostolos Panagiotopoulos, John Gkountouras, Konstantinos Papakostas, Wilker Aziz
Pubblicato in: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, ISSN 2160-7516
Editore: IEEE / Computer Vision Foundation (CVF)
DOI: 10.1109/CVPRW59228.2023.00388

Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?

Autori: Joris Baan, Raquel Fernández, Barbara Plank, Wilker Aziz
Pubblicato in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024
Editore: Association for Computational Linguistics
DOI: 10.48550/arXiv.2402.16102

Python Code Generation by Asking Clarification Questions

Autori: Li, Haau-Sing; Mesgar, Mohsen; Martins, André F. T.; Gurevych, Iryna
Pubblicato in: 2023
Editore: Association for Computational Linguistics
DOI: 10.48550/arxiv.2212.09885

Contrastive decoding reduces hallucinations in large multilingual machine translation models

Autori: Jonas Waldendorf, Barry Haddow, and Alexandra Birch
Pubblicato in: 2024
Editore: Proceedings of EACL 2024

Exploring very low-resource translation with LLMs: The University of Edinburgh’s submission to AmericasNLP 2024 translation task

Autori: Vivek Iyer, Bhavitvya Malik, Wenhao Zhu, Pavel Stepachev, Pinzhen Chen, Barry Haddow, Alexandra Birch
Pubblicato in: 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.AMERICASNLP-1.25

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

Autori: Chrysoula Zerva, Frederic Blain, José G. C. De Souza, Diptesh Kanojia, Sourabh Deoghare, Nuno M. Guerreiro, Giuseppe Attanasio, Ricardo Rei, Constantin Orasan, Matteo Negri, Marco Turchi, Rajen Chatterjee, Pushpak Bhattacharyya, Markus Freitag, André Mart
Pubblicato in: 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.3

BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation

Autori: Glushkova, Taisiya; Zerva, Chrysoula; Martins, André F. T.
Pubblicato in: 2023
Editore: Proceedings of EAMT 2023
DOI: 10.48550/arxiv.2305.19144

MGen: Millions of Naturally Occurring Generics in Context

Autori: Gustavo Cilleruelo, Emily Allaway, Barry Haddow, Alexandra Birch
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2509.26160

SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages

Autori: Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard, Caroline Brun, James Henderson, Laurent Besacier
Pubblicato in: No journal title, 2022
Editore: arXiv
DOI: 10.48550/arXiv.2210.11621

Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral.

Autori: António Farinhas, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei, André F.T. Martins
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2502.12701

A Conformal Risk Control Framework for Granular Word Assessment and Uncertainty Calibration of CLIPScore Quality Estimates

Autori: Goncalo Emanuel Cavaco Gomes, Bruno Martins, Chrysoula Zerva
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-ACL.638

Sharing matters: Analysing neurons across languages and tasks in llms

Autori: Weixuan Wang, Barry Haddow, Minghao Wu, Wei Peng, Alexandra Birch
Pubblicato in: 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2406.09265

Unbabel-IST at the WMT Chat Translation Shared Task

Autori: João Alves, Pedro Henrique Martins, José G. C. de Souza, M. Amin Farajian, André F. T. Martins
Pubblicato in: 2022
Editore: Association for Computational Linguistics

Context-Aware or Context-Insensitive? Assessing LLMs’ Performance in Document-Level Translation

Autori: Wafaa Mohammed, Vlad Niculae
Pubblicato in: 2025
Editore: European Association for Machine Translation

Findings of the IWSLT 2025 Evaluation Campaign

Autori: Idris Abdulmumin, Victor Agostinelli, Tanel Alumäe, Antonios Anastasopoulos, Luisa Bentivogli, Ondřej Bojar, Claudia Borg, Fethi Bougares, Roldano Cattoni, Mauro Cettolo, Lizhong Chen, William Chen, Raj Dabre, Yannick Estève, Marcello Federico, Mark Fishe
Pubblicato in: 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.IWSLT-1.44

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

Predict the Next Word: <Humans exhibit uncertainty in this task and language models _____>

Autori: Evgenia Ilia, Wilker Aziz
Pubblicato in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024
Editore: Association for Computational Linguistics
DOI: 10.48550/arXiv.2402.17527

Learning to vary: Teaching LMs to reproduce human linguistic variability in next- word prediction

Autori: Tobias Groot, Salo Lacunes, Evgenia Ilia
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2509.17794

Sparse Activations as Conformal Predictors

Autori: Margarida M Campos, João Cálem, Sophia Sklaviadis, Mario A. T. Figueiredo, Andre Martins
Pubblicato in: AISTATS 2025, 2025
Editore: PMLR

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: NeurIPS 202, 2024
Editore: Neural Information Processing Systems Foundation

Non-Exchangeable Conformal Risk Control

Autori: Farinhas, António; Zerva, Chrysoula; Ulmer, Dennis; Martins, André F. T.
Pubblicato in: 2023
Editore: arxiv
DOI: 10.48550/arxiv.2310.01262

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: EMNLP, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.EMNLP-MAIN.803

Findings of the WMT25 Shared Task on Automated Translation Evaluation Systems: Linguistic Diversity is Challenging and References Still Help

Autori: Alon Lavie, Greg Hanneman, Sweta Agrawal, Diptesh Kanojia, Chi kiu Lo, Vilem Zouhar, ´ Fred´ eric Blain, Chrysoula Zerva, Eleftherios Avramidis, Sourabh Deoghare, Archchana Sindhu- ´ jan, Jiayi Wang, David I. Adelani, Brian Thompson, Tom Kocmi, Markus Fre
Pubblicato in: 2025
Editore: Association for Computational Linguistics

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

Autori: Miguel Ramos, Patrick Fernandes, António Farinhas, Andre Martins
Pubblicato in: 2024
Editore: European Association for Machine Translation (EAMT)

Are LLMs Breaking MT Metrics? Results of the WMT24 Metrics Shared Task

Autori: Markus Freitag, Nitika Mathur, Daniel Deutsch, Chi-Kiu Lo, Eleftherios Avramidis, Ricardo Rei, Brian Thompson, Frederic Blain, Tom Kocmi, Jiayi Wang, David Ifeoluwa Adelani, Marianna Buchicchio, Chrysoula Zerva, Alon Lavie
Pubblicato in: Proceedings of the Ninth Conference on Machine Translation, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.WMT-1.2

Empowering Multi-step Reasoning across Languages via Program-Aided Language Models

Autori: Leonardo Ranaldi, Giulia Pucci, Barry Haddow, Alexandra Birch
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.678

TOWER-V2: Unbabel-IST 2024 Submission for the General MT Shared Task

Autori: Ricardo Rei, Jose Pombal, Nuno M. Guerreiro, João Alves, Pedro Henrique Martins, Patrick Fernandes, Helena Wu, Tania Vaz, Duarte Alves, Amin Farajian, Sweta Agrawal, Antonio Farinhas, José G. C. De Souza, André Martins
Pubblicato in: WMT 2024, 2024
Editore: Association for Computational Linguistics

Generics are puzzling. Can language models find the missing piece?

Autori: Wenhao Zhu, Pinzhen Chen, Hanxu Hu, Shujian Huang, Fei Yuan, Jiajun Chen, Alexandra Birch
Pubblicato in: COLING, 2025
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2502.15592

Reranking Laws for Language Generation: A Communication-Theoretic Perspective

Autori: António Farinhas ~António_Farinhas1 , Haau-Sing Li, Andre Martins
Pubblicato in: NeurIPS 2024, 2024
Editore: Neural Information Processing Systems Foundation
DOI: 10.48550/ARXIV.2409.07131

XTOWER: A Multilingual LLM for Explaining and Correcting Translation Errors

Autori: Marcos Treviso, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei, José Pombal, Tania Vaz, Helena Wu, Beatriz Silva, Daan van Stigt, André F. T. Martins
Pubblicato in: EMNLP 2024, 2024
Editore: Association for Computational Linguistics

Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations

Autori: Leonardo Ranaldi, Federico Ranaldi, Fabio Massimo Zanzotto, Barry Haddow, Alexandra Birch
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2504.04771

The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics

Autori: Nikolay Bogoychev, Pinzhen Chen, Barry Haddow, Alexandra Birch
Pubblicato in: https://aclanthology.org/2024.insights-1.17/, 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.INSIGHTS-1.17

Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models.

Autori: José Pombal, Nuno M. Guerreiro, Ricardo Rei, André F. T. Martins
Pubblicato in: COLM 2025, 2025
Editore: COLM 2025
DOI: 10.48550/ARXIV.2504.01001

Generics are puzzling. Can language models find the missing piece?

Autori: Gustavo Cilleruelo, Emily Allaway, Barry Haddow, Alexandra Birch
Pubblicato in: 2025
Editore: Association for Computational Linguistics

When Does Translation Require Context? A Data-driven, Multilingual Exploration

Autori: Patrick Fernandes, Kayo Yin, Emmy Liu, André F. T. Martins, Graham Neubig
Pubblicato in: 2023
Editore: Proceedings of ACL
DOI: 10.48550/ARXIV.2109.07446

Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets

Autori: Nikita Moghe, Arnisa Fazla, Chantal Amrhein, Tom Kocmi, Mark Steedman, Alexandra Birch, Rico Sennrich, Liane Guillou
Pubblicato in: Computational Linguistics, 2025, ISSN 0891-2017
Editore: MIT Press
DOI: 10.1162/coli_a_00537

Hallucinations in Large Multilingual Translation Models

Autori: Guerreiro, Nuno M.; Alves, Duarte; Waldendorf, Jonas; Haddow, Barry; Birch, Alexandra; Colombo, Pierre; Martins, André F. T.
Pubblicato in: Transactions of the Association for Computational Linguistics, 2023, ISSN 2307-387X
Editore: Transactions of the ACL
DOI: 10.1162/tacl_a_00615

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

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

Autori: Sweta Agrawal, Amin Farajian, Patrick Fernandes, Ricardo Rei, 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_00700

LeBenchmark 2.0: A standardized, replicable and enhanced framework for self-supervised representations of French speech

Autori: Titouan Parcollet, Ha Nguyen, Solène Evain, Marcely Zanon Boito, Adrien Pupier, Salima Mdhaffar, Hang Le, Sina Alisamir, Natalia Tomashenko, Marco Dinarelli, Shucong Zhang, Alexandre Allauzen, Maximin Coavoux, Yannick Estève, Mickael Rouvier, Jerôme Gouli
Pubblicato in: Computer Speech and Language 86, 2024, ISSN 0885-2308
Editore: Academic Press
DOI: 10.1016/j.csl.2024.101622

Efficient Methods for Natural Language Processing: A Survey

Autori: Treviso, Marcos; Lee, Ji-Ung; Ji, Tianchu; van Aken, Betty; Cao, Qingqing; Ciosici, Manuel R.; Hassid, Michael; Heafield, Kenneth; Hooker, Sara; Raffel, Colin; Martins, Pedro H.; Martins, André F. T.; Forde, Jessica Zosa; Milder, Peter; Simpson, Edwin; Slonim, Noam; Dodge, Jesse; Strubell, Emma; Balasubramanian, Niranjan; Derczynski, Leon; Gurevych, Iryna; Schwartz, Roy
Pubblicato in: Transactions of the Association for Computational Linguistics, 2023, ISSN 2307-387X
Editore: MIT press direct
DOI: 10.1162/tacl_a_00577

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

Autori: Fernandes, Patrick; Madaan, Aman; Liu, Emmy; Farinhas, António; Martins, Pedro Henrique; Bertsch, Amanda; de Souza, José G. C.; Zhou, Shuyan; Wu, Tongshuang; Neubig, Graham; Martins, André F. T.
Pubblicato in: Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation, 2023, ISSN 2307-387X
Editore: Transactions of the Association for Computational Linguistics
DOI: 10.1162/tacl_a_00626

Conformalizing Machine Translation Evaluation

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

Two derivations of Principal Component Analysis on datasets of distributions

Autori: Niculae, Vlad
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arxiv.2306.13503

Discrete Latent Structure in Neural Networks

Autori: Niculae, Vlad; Corro, Caio F.; Nangia, Nikita; Mihaylova, Tsvetomila; Martins, André F. T.
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arxiv.2301.07473

Cache & distil: Optimising API calls to large language models

Autori: Guillem Ramírez, Matthias Lindemann, Alexandra Birch, Ivan Titov
Pubblicato in: 2024
Editore: Arxiv
DOI: 10.48550/arXiv.2310.13561

The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation

Autori: Tokarchuk, Evgeniia; Niculae, Vlad
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arxiv.2310.20620

Context-aware Neural Machine Translation for English-Japanese Business Scene Dialogues

Autori: Honda, Sumire; Fernandes, Patrick; Zerva, Chrysoula
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arxiv.2311.11976

Iterative translation refinement with large language models,

Autori: Pinzhen Chen, Zhicheng Guo, Barry Haddow, and Kenneth Heafield
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arXiv.2306.03856

EUROLLM MULTILINGUAL LANGUAGE MODELS FOR EUROPE

Autori: Pedro Henrique Martins, Patrick Fernandes, João Alves, Nuno M. Guerreiro, Ricardo Rei, Duarte M. Alves, José Pombal, Amin Farajian, Manuel Faysse, Mateusz Klimaszewski, Pierre Colombo, Barry Haddow, José G. C. de Souza, Alexandra Birch, André F. T. Martin
Pubblicato in: 2022
Editore: arXiv

CroissantLLM: A Truly Bilingual French-English Language Model

Autori: Manuel Faysse, Patrick Fernandes, Nuno Guerreiro, António Loison, Duarte Alves, Caio Corro, Nicolas Boizard, Jaoe Alves, Ricardo Rei, Pedro Raphaël Martins, Antoni Casademunt, François Yvon, André Martins, Gautier Viaud, Céline Hudelot, Pierre Colombo
Pubblicato in: HAL, 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2402.00786

XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation

Autori: Vivek Iyer, Pinzhen Chen, Ricardo Rei, Alexandra Birch
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2503.22973

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

Autori: Lin, Peiqin; Hu, Chengzhi; Zhang, Zheyu; Martins, André F. T.; Schütze, Hinrich
Pubblicato in: 2023
Editore: arxiv
DOI: 10.48550/arxiv.2305.13684

Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets

Autori: Nikita Moghe, Arnisa Fazla, Chantal Amrhein, Tom Kocmi, Mark Steedman, Alexandra Birch, Rico Sennrich, Liane Guillou
Pubblicato in: 2024
Editore: Journal of Computational Linguistics
DOI: 10.48550/arXiv.2401.16313

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: 2024
Editore: arXiv
DOI: 10.48550/ARXIV.2305.13684

Retrieval-augmented multilingual knowledge editing

Autori: Weixuan Wang, Barry Haddow, and Alexandra Birch
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arXiv.2312.13040

A Context-aware Framework for Translation-mediated Conversations

Autori: José Pombal, Sweta Agrawal, Patrick Fernandes, Emmanouil Zaranis, André F. T. Martins
Pubblicato in: 2024
Editore: arXiv

Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task

Autori: Leonardo Ranaldi, Barry Haddow, Alexandra Birch
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2504.03616

Demystifying multilingual chain-of-thought in process reward modeling

Autori: W Wang, M Wu, B Haddow, A Birch
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2502.12663

Assessing the reliability of large language model knowledge

Autori: Weixuan Wang, Barry Haddow, Alexandra Birch, and Wei Peng
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arXiv.2310.09820

xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection

Autori: Guerreiro, Nuno M.; Rei, Ricardo; van Stigt, Daan; Coheur, Luisa; Colombo, Pierre; Martins, André F. T.
Pubblicato in: 2023
Editore: arxiv
DOI: 10.48550/arxiv.2310.10482

Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs

Autori: Ricardo Rei, Nuno M. Guerreiro, José Pombal, João Alves, Pedro Teixeirinha, Amin Farajian, André F. T. Martins
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2506.17080

Uncertainty in Natural Language Generation: From Theory to Applications

Autori: Baan, Joris; Daheim, Nico; Ilia, Evgenia; Ulmer, Dennis; Li, Haau-Sing; Fernández, Raquel; Plank, Barbara; Sennrich, Rico; Zerva, Chrysoula; Aziz, Wilker
Pubblicato in: 2023
Editore: arxiv
DOI: 10.48550/arxiv.2307.15703

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

Autori: Alves, Duarte M.; Guerreiro, Nuno M.; Alves, João; Pombal, José; Rei, Ricardo; de Souza, José G. C.; Colombo, Pierre; Martins, André F. T.
Pubblicato in: ACL Anthology, 2023
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-emnlp.744

Question Translation Training for Better Multilingual Reasoning

Autori: Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch
Pubblicato in: 2024
Editore: Arxiv
DOI: 10.48550/arXiv.2401.07817

Long-Context Generalization with Sparse Attention

Autori: Vasylenko, Pavlo ; Pitorro, Hugo ; Martins, André F. T. ; Treviso, Marcos
Pubblicato in: 2025
Editore: arxiv
DOI: 10.48550/ARXIV.2506.16640

Dialogue Quality and Emotion Annotations for Customer Support Conversations

Autori: Mendonça, John; Pereira, Patrícia; Menezes, Miguel; Cabarrão, Vera; Farinha, Ana C.; Moniz, Helena; Carvalho, João Paulo; Lavie, Alon; Trancoso, Isabel
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arxiv.2311.13910

When does monolingual data help multilingual translation: The role of domain and model scale

Autori: Christos Baziotis, Biao Zhang, Alexandra Birch, and Barry Haddow
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arXiv.2305.14124

Learning to Scaffold: Optimizing Model Explanations for Teaching

Autori: Fernandes, Patrick; Treviso, Marcos; Pruthi, Danish; Martins, André F. T.; Neubig, Graham
Pubblicato in: 2022
Editore: arxiv
DOI: 10.48550/arXiv.2204.10810

Large language model inference with lexical shortlisting,

Autori: Nikolay Bogoychev, Pinzhen Chen, Barry Haddow, and Alexandra Birch
Pubblicato in: 2023
Editore: Arxiv
DOI: 10.48550/arXiv.2311.09709

È in corso la ricerca di dati su OpenAIRE...

Risultati finali

Pubblicazioni

Condividi questa pagina Condividi questa pagina sui social network

Scarica Scarica il contenuto della pagina