High Performance Language Technologies

Risultati finali

Initial release of monolingual and parallel data sets

This deliverable consists of initial set of textual data acquired from web and non-web sources, both in monolingual and parallel parts, after cleaning done in WP2.

Software for cleaning data sets

Free and open-source software will be released on GitHub.

First language models trained

Language models will be made available for download however it may not have all or the cleanest data.

Translation models for select language pairs

Models available for download trained using the pipeline.

Pubblicazioni

A New Massive Multilingual Dataset for High-Performance Language Technologies

Autori: de Gibert, Ona; Nail, Graeme; Arefyev, Nikolay; Bañón, Marta; van der Linde, Jelmer; Ji, Shaoxiong; Zaragoza-Bernabeu, Jaume; Aulamo, Mikko; Ramírez-Sánchez, Gema; Kutuzov, Andrey; Pyysalo, Sampo; Oepen, Stephan; Tiedemann, Jörg
Pubblicato in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, ISSN 1530-9312
Editore: ELRA and ICCL
DOI: 10.48550/ARXIV.2403.14009

SpringerPlus

Autori: Tiedemann J.; Aulamo M.; Bakshandaeva D.; Boggia M.; Grönroos S. A.; Nieminen T.; Raganato A.; Scherrer Y.; Vázquez R.; Virpioja S.
Pubblicato in: Springer, 2023, ISSN 2193-1801
Editore: Springer Science and Business Media Deutschland GmbH
DOI: 10.48550/ARXIV.2212.01936

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

Autori: Shaoxiong Ji; Zihao Li; Indraneil Paul; Jaakko Paavola; Peiqin Lin; Pinzhen Chen; Dayyán O'Brien; Hengyu Luo; Hinrich Schütze; Jörg Tiedemann; Barry Haddow
Pubblicato in: CoRR, 2024, ISSN 2331-8422
Editore: ArXiv
DOI: 10.48550/ARXIV.2409.17892

Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?

Autori: Shaoxiong Ji; Timothee Mickus; Vincent Segonne; Jörg Tiedemann
Pubblicato in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, ISSN 1530-9312
Editore: ELRA and ICCL
DOI: 10.48550/ARXIV.2403.16777

An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)

Autori: Laurie Burchell; Ona de Gibert; Nikolay Arefyev; Mikko Aulamo; Marta Bañón; Pinzhen Chen; Mariia Fedorova; Liane Guillou; Barry Haddow; Jan Hajic; Jindrich Helcl; Erik Henriksson; Mateusz Klimaszewski; Ville Komulainen; Andrey Kutuzov; Joona Kytöniemi; Veronika Laippala; Petter Mæhlum; Bhavitvya Malik; Farrokh Mehryary; Vladislav Mikhailov; Nikita Moghe; Amanda Myntti; Dayyán O'Brien; Stephan Oepen; Proyag Pal; Jousia Piha; Sampo Pyysalo; Gema Ramírez-Sánchez; David Samuel; Pavel Stepachev; Jörg Tiedemann; Dusan Varis; Tereza Vojtechová; Jaume Zaragoza-Bernabeu
Pubblicato in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2503.10267

Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?

Autori: Pinzhen Chen; Simon Yu; Zhicheng Guo; Barry Haddow
Pubblicato in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2406.12822

Poro 34B and the Blessing of Multilinguality

Autori: Luukkonen, Risto; Burdge, Jonathan; Zosa, Elaine; Talman, Aarne; Komulainen, Ville; Hatanpää, Väinö; Sarlin, Peter; Pyysalo, Sampo
Pubblicato in: CoRR, 2024, ISSN 2331-8422
Editore: ArXiv
DOI: 10.48550/ARXIV.2404.01856

How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM

Autori: Ji, Shaoxiong; Chen, Pinzhen
Pubblicato in: CoRR, 2024, ISSN 2331-8422
Editore: ArXiv
DOI: 10.48550/ARXIV.2404.04850

GPT or BERT: why not both?

Autori: Lucas Georges Gabriel Charpentier, David Samuel
Pubblicato in: The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning, 2024, ISSN 1530-9312
Editore: Association for Computational Linguistics

Four Approaches to Low-Resource Multilingual NMT: The Helsinki Submission to the AmericasNLP 2023 Shared Task

Autori: Ona De Gibert, Raúl Vázquez, Mikko Aulamo, Yves Scherrer, Sami Virpioja, Jörg Tiedemann
Pubblicato in: 2023, ISBN 978-1-959429-91-3
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.AMERICASNLP-1.20

CUNI Systems for the WMT22 Czech-Ukrainian Translation Task

Autori: Popel, Martin; Libovický, Jindřich; Helcl, Jindřich
Pubblicato in: 2022, ISBN 978-1-959429-29-6
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2212.00486

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

Autori: Ashok Urlana, Pinzhen Chen, Zheng Zhao, Shay Cohen, Manish Shrivastava, Barry Haddow
Pubblicato in: 2023, ISBN 979-8-89176-061-5
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.FINDINGS-EMNLP.777

Towards Effective Disambiguation for Machine Translation with Large Language Models

Autori: Vivek Iyer, Pinzhen Chen, and Alexandra Birch
Pubblicato in: 2023, ISBN 979-8-89176-041-7
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.WMT-1.44

DocHPLT: A Massively Multilingual Document-Level Translation Dataset

Autori: Dayyán O’Brien, Bhavitvya Malik, Ona de Gibert, Pinzhen Chen, Barry Haddow, Jörg Tiedemann
Pubblicato in: Proceedings of the Tenth Conference on Machine Translation, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.WMT-1.17

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 Murray, Makoto Nagata, Toshiaki Nakazawa, Martin Popel, Maja Popović, Mariya Shmatova
Pubblicato in: Proceedings of the Eighth Conference on Machine Translation, 2023, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.WMT-1.1

FinGPT: Large Generative Models for a Small Language

Autori: Luukkonen, Risto; Komulainen, Ville; Luoma, Jouni; Eskelinen, Anni; Kanerva, Jenna; Kupari, Hanna-Mari; Ginter, Filip; Laippala, Veronika; Muennighoff, Niklas; Piktus, Aleksandra; Wang, Thomas; Tazi, Nouamane; Scao, Teven Le; Wolf, Thomas; Suominen, Osma; Sairanen, Samuli; Merioksa, Mikko; Heinonen, Jyrki; Vahtola, Aija; Antao, Samuel; Pyysalo, Sampo
Pubblicato in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, ISBN 979-8-89176-060-8
Editore: Association for Computational Linguistics
DOI: 10.48550/arxiv.2311.05640

Abstractive Event Analysis of Armed Conflicts: Introducing the UCDP-AEC Dataset

Autori: Étienne Simon, Helene Bøsei Olsen, Ramón Carreño, Rahul Mishra, Nikolay Arefyev, Mert Can Yilmaz, Lilja Øvrelid, Erik Velldal
Pubblicato in: Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025): Workshops, 2025
Editore: HsH Applied Academics

Scaling Low-Resource MT via Synthetic Data Generation with LLMs

Autori: Ona de Gibert, Joseph Attieh, Teemu Vahtola, Mikko Aulamo, Zihao Li, Raúl Vázquez, Tiancheng Hu, Jörg Tiedemann
Pubblicato in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.EMNLP-MAIN.1408

Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings

Autori: David Samuel
Pubblicato in: Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, 2023, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.CONLL-BABYLM.19

NorBench – A Benchmark for Norwegian Language Models

Autori: David Samuel, Andrey Kutuzov, Samia Touileb, Erik Velldal, Lilja Øvrelid, Egil Rønningstad, Elina Sigdel, Anna Palatkina
Pubblicato in: Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), 2023
Editore: University of Tartu Library

Got Compute, but No Data: Lessons From Post-training a Finnish LLM

Autori: Elaine Zosa, Ville Komulainen, Sampo Pyysalo
Pubblicato in: : Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), 2025
Editore: University of Tartu Library

Findings of the WMT25 General Machine Translation Shared Task: Time to Stop Evaluating on Easy Test Sets

Autori: Tom Kocmi, Ekaterina Artemova, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Konstantin Dranch, Anton Dvorkovich, Sergey Dukanov, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Howard Lakougna, Jessica Lundin, Christof Monz, Kenton Murray, Masaaki Nagata, Stefano Perrella, Lorenzo Proietti, Martin Popel, Maja Popović, Parker Riley, Mariya Shmatova, Steinthór Steingrímsson, Lisa Yankovskaya, Vilém Zouhar
Pubblicato in: Proceedings of the Tenth Conference on Machine Translation, 2025, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.WMT-1.22

Tokenization with Factorized Subword Encoding

Autori: David Samuel and Lilja Øvrelid
Pubblicato in: 2023, ISBN 978-1-959429-62-3
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.FINDINGS-ACL.890

FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering

Autori: Erik Henriksson, Otto Tarkka, Filip Ginter
Pubblicato in: Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), 2025
Editore: University of Tartu Library

Cher at KSAA-CAD 2024: Compressing Words and Definitions into the Same Space for Arabic Reverse Dictionary

Autori: Pinzhen Chen, Zheng Zhao, Shun Shao
Pubblicato in: Proceedings of The Second Arabic Natural Language Processing Conference, 2024, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.ARABICNLP-1.75

Towards Interpretable Mental Health Analysis with Large Language Models

Autori: Yang, Kailai; Ji, Shaoxiong; Zhang, Tianlin; Xie, Qianqian; Kuang, Ziyan; Ananiadou, Sophia
Pubblicato in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, ISBN 979-8-89176-060-8
Editore: Association for Computational Linguistics
DOI: 10.48550/arxiv.2304.03347

Findings of the AmericasNLP 2025 Shared Tasks on Machine Translation, Creation of Educational Material, and Translation Metrics for Indigenous Languages of the Americas

Autori: Ona De Gibert, Robert Pugh, Ali Marashian, Raul Vazquez, Abteen Ebrahimi, Pavel Denisov, Enora Rice, Edward Gow-Smith, Juan Prieto, Melissa Robles, Rubén Manrique, Oscar Moreno, Angel Lino, Rolando Coto-Solano, Aldo Alvarez, Marvin Agüero-Torales, John E. Ortega, Luis Chiruzzo, Arturo Oncevay, Shruti Rijhwani, Katharina Von Der Wense, Manuel Mager
Pubblicato in: Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP), 2025, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.AMERICASNLP-1.16

The OPUS-MT Dashboard – A Toolkit for a Systematic Evaluation of Open Machine Translation Models

Autori: Jörg Tiedemann and Ona de Gibert
Pubblicato in: 2023, ISBN 978-1-959429-70-8
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.ACL-DEMO.30

Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting

Autori: Bogoychev, Nikolay and Chen, Pinzhen
Pubblicato in: 2023, ISBN 979-8-89176-041-7
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.WMT-1.80

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

Autori: Chen, Pinzhen; Ji, Shaoxiong; Bogoychev, Nikolay; Kutuzov, Andrey; Haddow, Barry; Heafield, Kenneth
Pubblicato in: EACL, 2023, ISBN 979-8-89176-088-2
Editore: Association for Computational Linguistics
DOI: 10.48550/arxiv.2309.08958

Fine-Tuning Large Language Models with Sequential Instructions

Autori: Hanxu Hu, Simon Yu, Pinzhen Chen, Edoardo Ponti
Pubblicato in: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2025, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.NAACL-LONG.288

HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models

Autori: Stephan Oepen and Nikolay Arefev and Mikko Aulamo and Marta Bañón and Maja Buljan and Laurie Burchell and Lucas Charpentier and Pinzhen Chen and Mariya Fedorova and Ona de Gibert and Barry Haddow and Jan Hajič and Jindřich Helcl and Andrey Kutuzov and Ver
Pubblicato in: Proceedings of the Fifteenth Language Resources and Evaluation Conference, 2026, ISSN 2522-2686
Editore: International Conference on Language Resources and Evaluation

An Open Dataset and Model for Language Identification

Autori: Laurie Burchell, Alexandra Birch, Nikolay Bogoychev, Kenneth Heafield
Pubblicato in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.ACL-SHORT.75

Unsupervised Feature Selection for Effective Parallel Corpus Filtering

Autori: Mikko Aulamo, Ona de Gibert, Sami Virpioja, and Jörg Tiedemann
Pubblicato in: Proceedings of the 24th Annual Conference of the European Association for Machine Translation, 2023, ISBN 978-952-03-2947-1
Editore: European Association for Machine Translation

Exploring Data Augmentation for Code Generation Tasks

Autori: Pinzhen Chen, Gerasimos Lampouras
Pubblicato in: 2023, ISBN 978-1-959429-47-0
Editore: Association for Computational Linguistics

Scaling Data-Constrained Language Models

Autori: Muennighoff, Niklas; Rush, Alexander M.; Barak, Boaz; Scao, Teven Le; Piktus, Aleksandra; Tazi, Nouamane; Pyysalo, Sampo; Wolf, Thomas; Raffel, Colin
Pubblicato in: 2023, ISSN 2331-8422
Editore: NeurIPS'23
DOI: 10.48550/arxiv.2305.16264

CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

Autori: Helcl, Jindřich
Pubblicato in: 2022, ISBN 978-1-959429-29-6
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2212.00477

Code-Switched Language Identification is Harder Than You Think

Autori: Burchell, Laurie and Birch, Alexandra and Thompson, Robert and Heafield, Kenneth
Pubblicato in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, ISSN 1530-9312
Editore: Association for Computational Linguistics

CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

Autori: Jindřich Helcl
Pubblicato in: Proceedings of the Seventh Conference on Machine Translation (WMT), 2022, ISSN 1530-9312
Editore: Association for Computational Linguistics

HPLT’s First Release of Data and Models

Autori: Ramírez-Sánchez, Gema; Chen, Pinzhen; Helcl, Jindřich; Zaragoza-Bernabeu, Jaume; Malik, Bhavitvya; De Gibert Bonet, Ona; Stepachev, Pavel; Variš, Dušan; Haddow, Barry; Arefyev, Nikolay; Tiedemann, Jörg
Pubblicato in: 2024, ISSN 1530-9312
Editore: European Association for Machine Translation (EAMT)

OpusDistillery: A Configurable End-to-End Pipeline for Systematic Multilingual Distillation of Open NMT Models

Autori: Ona de Gibert, Tommi Nieminen, Yves Scherrer, Jörg Tiedemann
Pubblicato in: Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), 2025
Editore: University of Tartu Library

HPLT’s Second Data Release

Autori: Nikolay Arefyev, Mikko Aulamo, Marta Bañón, Laurie Burchell, Pinzhen Chen, Mariia Fedorova, Ona de Gibert, Liane Guillou, Barry Haddow, Jan Hajič, Jindřich Helcl, Erik Henriksson, Andrey Kutuzov, Veronika Laippala, Bhavitvya Malik, Farrokh Mehryary, Vladi
Pubblicato in: Proceedings of Machine Translation Summit XX: Volume 2, 2025
Editore: European Association for Machine Translation

Mind the Gap: Diverse NMT Models for Resource-Constrained Environments

Autori: Ona de Gibert, Dayyán O’Brien, Dušan Variš, Jörg Tiedemann
Pubblicato in: Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), 2025
Editore: University of Tartu Library

Cheating to Identify Hard Problems for Neural Machine Translation

Autori: Proyag Pal, Kenneth Heafield
Pubblicato in: 2023, ISBN 978-1-959429-47-0
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.FINDINGS-EACL.120

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: Proceedings of the Fifth Workshop on Insights from Negative Results in NLP, 2024, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.INSIGHTS-1.17

Large Language Model Inference with Lexical Shortlisting

Autori: Nikolay Bogoychev and Pinzhen Chen and Barry Haddow and Alexandra Birch
Pubblicato in: AAAI Workshop on Deployable AI, 2024, ISSN 2331-8422
Editore: arXiv
DOI: 10.48550/ARXIV.2311.09709

Not all layers are equally as important: Every Layer Counts BERT

Autori: Lucas Georges Gabriel Charpentier, David Samuel
Pubblicato in: Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, 2023, ISSN 1530-9312
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2023.CONLL-BABYLM.20

HPLT High-Performance Language Technology: Building LLMs and TMs in European languages

Autori: Hajič, Jan
Pubblicato in: 2023
Editore: Oral presentation at Skeikampen, Norway

Iterative Translation Refinement with Large Language Models

Autori: Chen, Pinzhen and Guo, Zhicheng and Haddow, Barry and Heafield, Kenneth
Pubblicato in: 2023, ISSN 2331-8422
Editore: arXiv
DOI: 10.48550/ARXIV.2306.03856

{EEE-QA}: Exploring effective and efficient question-answer representations

Autori: Zhanghao Hu and Yijun Yang and Junjie Xu and Yifu Qiu and Pinzhen Chen
Pubblicato in: 2024, ISSN 2331-8422
Editore: arXiv
DOI: 10.48550/ARXIV.2403.02176

Velké jazykové modely: Co znamená velké a co jazykové?

Autori: Libovický, Jindřich
Pubblicato in: 2023
Editore: Talk at FI MUNI, Brno, Czechia

OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models

Autori: Nikolay Bogoychev and Jelmer van der Linde and Graeme Nail and Barry Haddow and Jaume Zaragoza-Bernabeu and Gema Ramírez-Sánchez and Lukas Weymann and Tudor Nicolae Mateiu and Jindřich Helcl and Mikko Aulamo
Pubblicato in: 2023, ISSN 2331-8422
Editore: arXiv
DOI: 10.48550/ARXIV.2311.14838

Risultati finali

Pubblicazioni

Condividi questa pagina Condividi questa pagina sui social network

Scarica il PDF Scarica il contenuto della pagina