Found in Translation – Natural Language Understanding with Cross-Lingual Grounding | FoTran | Proyecto | Resultados | H2020 | CORDIS

TaPaCo: A Corpus of Sentential Paraphrases for 73 Languages

Autores: Yves Scherrer
Publicado en: Proceedings of The 12th Language Resources and Evaluation Conference, 2020, Página(s) 6868-6873, ISBN 979-10-95546-34-4
Editor: European Language Resources Association (ELRA)

HeLju@VarDial 2020: Social Media Variety Geolocation with BERT Models

Autores: Yves Scherrer, Nikola Ljubešić
Publicado en: Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects, 2020, Página(s) 202-211, ISBN 978-1-952148-47-7
Editor: International Committee on Computational Linguistics (ICCL)

Boosting Neural Machine Translation from Finnish to Northern Sámi with Rule-Based Backtranslation

Autores: Mikko Aulamo, Sami Virpioja, Yves Scherrer, Jörg Tiedemann
Publicado en: 2021
Editor: Linköping University Electronic Press, Sweden

Paraphrase Generation and Evaluation on Colloquial-Style Sentences

Autores: Eetu Ilari Sjöblom, Mathias Creutz, Yves Scherrer
Publicado en: Proceedings of the 12th Language Resources and Evaluation Conference, 2020, Página(s) 1814-1822, ISBN 979-10-95546-34-4
Editor: European Language Resources Association (ELRA)

How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets

Autores: Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis, Jörg Tiedemann
Publicado en: 2022
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2022.starsem-1.20

Social Media Variety Geolocation with geoBERT

Autores: Yves Scherrer, Nikola Ljubešić
Publicado en: Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects, 2021
Editor: The Association for Computational Linguistics

OpusFilter: A Configurable Parallel Corpus Filtering Toolbox

Autores: Mikko Aulamo, Sami Virpioja, Jörg Tiedemann
Publicado en: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2020, Página(s) 150-156
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-demos.20

Grapheme-Based Cross-Language Forced Alignment: Results with Uralic Languages

Autores: Juho Leinonen, Sami Virpioja, Mikko Kurimo
Publicado en: 2021
Editor: Linköping University Electronic Press, Sweden

Grammatical Error Generation Based on Translated Fragments

Autores: Eetu Sjöblom, Mathias Creutz, Teemu Vahtola
Publicado en: 2021
Editor: Linköping University Electronic Press, Sweden

MULTISEM at SemEval-2020 Task 3: Fine-tuning BERT for Lexical Meaning

Autores: Aina Garí Soler, Marianna Apidianaki
Publicado en: Proceedings of the Fourteenth Workshop on Semantic Evaluation, Edición December 2020, 2020, Página(s) 158–165
Editor: International Committee for Computational Linguistics

Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models

Autores: Mittul Singh, Peter Smit, Sami Virpioja, Mikko Kurimo
Publicado en: Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), 2020, Página(s) 41-45, ISBN 979-10-95546-35-1
Editor: European Language Resources Association (ELRA)

The OPUS-MT dashboard - A toolkit for a systematic evaluation of open machine translation models

Autores: Jörg Tiedemann, Ona de Gibert
Publicado en: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023
Editor: Association for Computational Linguistics

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies

Autores: Aina Gari Soler, Marianna Apidianaki
Publicado en: 2021
Editor: The Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.370

Unsupervised Feature Selection for Effective Parallel Corpus Filtering

Autores: Mikko Aulamo, Ona de Gibert, Sami Virpioja, Jörg Tiedemann
Publicado en: Proceedings of the 24th Annual Conference of the European Association for Machine Translation, 2023
Editor: European Association for Machine Translation

Monolingual or Multilingual Instruction Tuning : Which Makes a Better Alpaca

Autores: Pinzhen Chen, Shaoxiong Ji, Nikolay Bogoychev and Barry Haddow and Kenneth Heafield
Publicado en: Findings of the Association for Computational Linguistics: EACL 2024, 2024
Editor: Findings of the Association for Computational Linguistics: EACL 2024
DOI: 10.48550/arxiv.2309.08958

Sesame Street to Mount Sinai: BERT-constrained character-level Moses models for multilingual lexical normalization

Autores: Yves Scherrer, Nikola Ljubešić
Publicado en: 2021
Editor: The Association for Computational Linguistics

Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning

Autores: Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo
Publicado en: Proceedings of The 12th Language Resources and Evaluation Conference, 2020, Página(s) 3944-3953, ISBN 979-10-95546-34-4
Editor: European Language Resources Association (ELRA)

FinChat: Corpus and Evaluation Setup for Finnish Chat Conversations on Everyday Topics

Autores: Katri Leino, Juho Leinonen, Mittul Singh, Sami Virpioja, Mikko Kurimo
Publicado en: Interspeech 2020, 2020, Página(s) 429-433
Editor: ISCA
DOI: 10.21437/interspeech.2020-2511

OPUS-MT -- Building open translation services for the World

Autores: Jörg Tiedemann, Santhosh Thottingal
Publicado en: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2020, Página(s) 479-480, ISBN 978-989-33-0589-8
Editor: European Association for Machine Translation

Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation

Autores: Alessandro Raganato, Yves Scherrer, Jörg Tiedemann
Publicado en: Findings of the Association for Computational Linguistics : EMNLP 2020, 2020, Página(s) 556-568, ISBN 978-1-952148-90-3
Editor: The Association for Computational Linguistics

The University of Helsinki and Aalto University submissions to the WMT 2020 news and low-resource translation tasks

Autores: Yves Scherrer, Stig-Arne Grönroos, Sami Virpioja
Publicado en: Proceedings of the Fifth Conference on Machine Translation, 2020, Página(s) 1129-1138, ISBN 978-1-948087-81-0
Editor: The Association for Computational Linguistics

Controlling the Imprint of Passivization and Negation in Contextualized Representations

Autores: Hande Celikkanat, Sami Virpioja, Jörg Tiedemann, Marianna Apidianaki
Publicado en: Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2020, Página(s) 136-148, ISBN 978-1-952148-86-6
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.blackboxnlp-1.13

NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance

Autores: Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis, Jörg Tiedemann
Publicado en: 2021
Editor: Linköping University Electronic Press, Sweden

Why bother with geometry?On the relevance of linear decompositions of Transformer embeddings

Autores: Timothee Mickus and Raúl Vázquez
Publicado en: Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, 2023, Página(s) 127–141
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2023.blackboxnlp-1.10

Definition Modeling : To model definitions. Generating Definitions With Little to No Semantics

Autores: Vincent Segonne, Timothee Mickus
Publicado en: 2023
Editor: Association for Computational Linguistics

A Closer Look at Parameter Contributions When Training Neural Language and Translation Models

Autores: Raúl Vázquez, Hande Celikkanat, Vinit Ravishankar, Mathias Creutz, Jörg Tiedemann
Publicado en: Proceedings of the 29th International Conference on Computational Linguistics, 2022, Página(s) 4788–4800
Editor: International Committee on Computational Linguistics

„Mann“ is to “Donna” as「国王」is to « Reine » Adapting the Analogy Task for Multilingual and Contextual Embeddings

Autores: Timothee Mickus, Eduardo Calò, Léo Jacqmin, Denis Paperno, Mathieu Constant
Publicado en: 2023
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2023.starsem-1.25

BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations

Autores: Aina Garí Soler, Marianna Apidianaki
Publicado en: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Página(s) 7371-7385
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.598

The MUCOW word sense disambiguation test suite at WMT 2020

Autores: Yves Scherrer, Alessandro Raganato, Jörg Tiedemann
Publicado en: Proceedings of the Fifth Conference on Machine Translation, 2020, Página(s) 365-370, ISBN 978-1-948087-81-0
Editor: The Association for Computational Linguistics

Latest Development in the FoTran Project – Scaling Up Language Coverage in Neural Machine Translation Using Distributed Training with Language-Specific Components

Autores: Raúl Vázquez, Michele Boggia, Alessandro Raganato, Niki A. Loppi, Stig-Arne Grönroos, Jörg Tiedemann
Publicado en: 2022
Editor: European Association for Machine Translation

Wikipedia Entities as Rendezvous across Languages: Grounding Multilingual Language Models by Predicting Wikipedia Hyperlinks

Autores: Iacer Calixto, Alessandro Raganato, Tommaso Pasini
Publicado en: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, Página(s) 3651-3661
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2021.naacl-main.286

The University of Helsinki Submission to the IWSLT2020 Offline SpeechTranslation Task

Autores: Raúl Vázquez, Mikko Aulamo, Umut Sulubacak, Jörg Tiedemann
Publicado en: Proceedings of the 17th International Conference on Spoken Language Translation, 2020, Página(s) 95-102, ISBN 978-1-952148-07-1
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.iwslt-1.10

Emerging Language Spaces Learned From Massively Multilingual Corpora. In Proceedings of the 3rd Conference on Digital Humanities in the Nordic Countries (DHN 2018), Helsinki, Finland

Autores: Tiedemann, Jörg
Publicado en: Proceedings of the Digital Humanities in the Nordic Countries 3rd Conference (DHN 2018), 2018, Página(s) 188-197
Editor: CEUR Workshop Proceedings

An Evaluation of Language-Agnostic Inner-Attention-Based Representations in Machine Translation

Autores: Alessandro Raganato, Raúl Vázquez, Mathias Creutz, Jörg Tiedemann
Publicado en: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), 2019, Página(s) 27-32, ISBN 978-1-950737-35-2
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-4304

The University of Helsinki Submissions to the WMT19 Similar Language Translation Task

Autores: Yves Scherrer, Raúl Vázquez, Sami Virpioja
Publicado en: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), 2019, Página(s) 236-244, ISBN 978-1-950737-27-7
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5432

The University of Helsinki Submissions to the WMT19 News Translation Task

Autores: Aarne Talman, Umut Sulubacak, Raúl Vázquez, Yves Scherrer, Sami Virpioja, Alessandro Raganato, Arvi Hurskainen, Jörg Tiedemann
Publicado en: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Página(s) 412-423, ISBN 978-1-950737-27-7
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5347

The University of Helsinki Submission to the WMT19 Parallel Corpus Filtering Task

Autores: Raúl Vázquez, Umut Sulubacak, Jörg Tiedemann
Publicado en: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), 2019, Página(s) 294-300, ISBN 978-1-950737-27-7
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5441

Multilingual NMT with a Language-Independent Attention Bridge

Autores: Raúl Vázquez, Alessandro Raganato, Jörg Tiedemann, Mathias Creutz
Publicado en: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), 2019, Página(s) 33-39, ISBN 978-1-950737-35-2
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-4305

SUM-QE: a BERT-based Summary Quality Estimation Model

Autores: Stratos Xenouleas, Prodromos Malakasiotis, Marianna Apidianaki, Ion Androutsopoulos
Publicado en: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, Página(s) 6004-6010
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/d19-1618

An Analysis of Encoder Representations in Transformer-Based Machine Translation

Autores: Alessandro Raganato, Jörg Tiedemann
Publicado en: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2018, Página(s) 287-297, ISBN 978-1-948087-71-1
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w18-5431

The University of Helsinki submissions to the WMT18 news task

Autores: Alessandro Raganato, Yves Scherrer, Tommi Nieminen, Arvi Hurskainen, Jörg Tiedemann
Publicado en: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, 2018, Página(s) 488-495, ISBN 978-1-948087-81-0
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w18-6425

The MuCoW test suite at WMT 2019: Automatically harvested multilingual contrastive word sense disambiguation test sets for machine translation.

Autores: Alessandro Raganato, Yves Scherrer, Jörg Tiedemann
Publicado en: In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop. 2019., 2019, Página(s) 470-480, ISBN 9781-950737277
Editor: The Association for Computational Linguistics

Analysing concatenation approaches to document-level NMT in two different domains

Autores: Yves Scherrer, Jörg Tiedemann, Sharid Loáiciga
Publicado en: Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), 2019, Página(s) 51-61, ISBN 978-1-950737-74-1
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/d19-6506

Measuring Semantic Abstraction of Multilingual

Autores: Jörg Tiedemann, Yves Scherrer
Publicado en: Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for, 2019, Página(s) 35-42, ISBN 978-1-950737-05-5
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-2005

The WMT’18 Morpheval test suites for English-Czech, English-German, English-Finnish and Turkish-English

Autores: Franck Burlot, Yves Scherrer, Vinit Ravishankar, Ondřej Bojar, Stig-Arne Grönroos, Maarit Koponen, Tommi Nieminen, François Yvon
Publicado en: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, 2018, Página(s) 546-560, ISBN 978-1-948087-81-0
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w18-6433

Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations

Autores: Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann, Martti Vainio
Publicado en: 22nd Nordic Conference on Computational Linguistics (NoDaLiDa) : Proceedings of the Conference, 2019, Página(s) 281–290, ISBN 978-91-7929-995-8
Editor: Linköping University Electronic Press

The University of Helsinki submissions to the IWSLT 2018 low-resource translation task

Autores: Yves Scherrer
Publicado en: Proceedings of the 15th International Workshop on Spoken Language Translation, 2018, Página(s) 83-88
Editor: International Workshop on Spoken Language Translation - Brugge, Belgium

Ensembles of Neural Morphological Inflection Models

Autores: Ilmari Kylliäinen, Miikka Silfverberg
Publicado en: Proceedings of the 22nd Nordic Conference on Computational Linguistics, 2019, Página(s) 304–309
Editor: Linköping University Electronic Press

Data-Driven Morphological Analysis for Uralic Languages

Autores: Miikka Silfverberg, Francis Tyers
Publicado en: Proceedings of the Fifth International Workshop on Computational Linguistics for Uralic Languages, 2019, Página(s) 1-14
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-0301

Weird Inflects but OK: Making Sense of Morphological Generation Errors

Autores: Kyle Gorman, Arya D. McCarthy, Ryan Cotterell, Ekaterina Vylomova, Miikka Silfverberg, Magdalena Markowska
Publicado en: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), 2019, Página(s) 140-151
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/k19-1014

The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection

Autores: Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sebastian J. Mielke, Jeffrey Heinz, Ryan Cotterell, Mans Hulden
Publicado en: Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2019, Página(s) 229-244
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/w19-4226

Towards Interpretable Mental Health Analysis with Large Language Models

Autores: Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang, Sophia Ananiadou
Publicado en: 2023
Editor: The Association for Computational Linguistics

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

Autores: Ona De Gibert, Raúl Vázquez, Mikko Aulamo, Yves Scherrer, Sami Virpioja, Jörg Tiedemann
Publicado en: 2023
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2023.americasnlp-1.20

The Helsinki submission to the AmericasNLP shared task

Autores: Raúl Vázquez, Yves Scherrer, Sami Virpioja, Jörg Tiedemann
Publicado en: Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, 2021, Página(s) 255-264
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2021.americasnlp-1.29

MAMMOTH : Massively Multilingual Modular Open Translation @ Helsinki

Autores: Timothee Mickus, Stig-Arne Grönroos, Joseph Attieh, Michele Boggia, Ona De Gibert, Shaoxiong Ji, Niki Andreas Loppi, Alessandro Raganato, Raúl Vázquez, Jörg Tiedemann
Publicado en: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024
Editor: Association for Computational Linguistics

Recent Trends in Word Sense Disambiguation: A Survey

Autores: Michele Bevilacqua, Tommaso Pasini, Alessandro Raganato, Roberto Navigli
Publicado en: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021, Página(s) 4330-4338, ISBN 978-0-9992411-9-6
Editor: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2021/593

Dozens of Translation Directions or Millions of Shared Parameters? Comparing Two Types of Multilinguality in Modular Machine Translation

Autores: Michele Boggia, Stig-Arne Grönroos, Niki Loppi, Timothee Mickus, Alessandro Raganato, Jörg Tiedemann, and Raúl Vázquez
Publicado en: Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), 2023
Editor: University of Tartu Library

On the differences between BERT and MT encoder spaces and how to address them in translation tasks

Autores: Raúl Vázquez, Hande Celikkanat, Mathias Creutz, Jörg Tiedemann
Publicado en: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, 2021, Página(s) 337-347
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2021.acl-srw.35

XL-WSD: An Extra-Large and Cross-Lingual Evaluation Framework for Word Sense Disambiguation

Autores: Tommaso Pasini, Alessandro Raganato, Roberto Navigli
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, 2021, ISBN 978-1-57735-866-4
Editor: AAAI Press
DOI: 10.1609/aaai.v35i15.17609

An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation

Autores: Alessandro Raganato, Raúl Vázquez, Mathias Creutz, Jörg Tiedemann
Publicado en: 2021
Editor: The Association for Computational Linguistics

Morfessor-enriched features and multilingual training for canonical morphological segmentation

Autores: Aku Rouhe, Stig-Arne Grönroos, Sami Virpioja, Mathias Creutz, Mikko Kurimo
Publicado en: 2022
Editor: The Association for Computational Linguistics
DOI: 10.18653/v1/2022.sigmorphon-1.16

XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization

Autores: Alessandro Raganato, Tommaso Pasini, Jose Camacho-Collados, Mohammad Taher Pilehvar
Publicado en: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Página(s) 7193-7206
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.584

OpusTools and Parallel Corpus Diagnostics

Autores: Mikko Aulamo, Umut Sulubacak, Sami Virpioja, Jörg Tiedemann
Publicado en: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), 2020, Página(s) 3782-3789, ISBN 979-10-95546-34-4
Editor: European Language Resources Association (ELRA)

The Tatoeba Translation Challenge - Realistic Data Sets for Low Resource and Multilingual MT

Autores: Jörg Tiedemann
Publicado en: Proceedings of the Fifth Conference on Machine Translation, 2020, Página(s) 1174-1182, ISBN 978-1-948087-81-0
Editor: The Association for Computational Linguistics

So many design choices: Improving and interpreting neural agent communication in signaling games

Autores: Timothée Bernard, Timothee Mickus
Publicado en: 2023
Editor: The Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-acl.531

Semiautomatic Speech Alignment for Under-Resourced Languages

Autores: Juho Leinonen, Niko Partanen, Sami Virpioja, Mikko Kurimo
Publicado en: 2022
Editor: European Language Resources Association (ELRA)

An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems

Autores: Alessandro Raganato, Yves Scherrer, Jörg Tiedemann
Publicado en: Proceedings of The 12th Language Resources and Evaluation Conference, 2020, Página(s) 3668-3675, ISBN 979-10-95546-34-4
Editor: European Language Resources Association (ELRA)

HELFI: a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment

Autores: Yli-Jyrä, Anssi; Purhonen, Josi; Liljeqvist, Matti; Antturi, Arto; Nieminen, Pekka; Räntilä, Kari M.; Luoto, Valtter
Publicado en: Proceedings of LREC, Edición 5, 2020
Editor: ELRA
DOI: 10.48550/arxiv.2003.07456

From open parallel corpora to public translation tools : The success story of OPUS

Autores: Tiedemann, Jörg
Publicado en: 2022
Editor: University of Göteborg

Grounded and well-rounded : a methodological approach to thestudy of cross-modal and cross-lingual grounding

Autores: Timothee Mickus, Elaine Zosa, Denis Paperno
Publicado en: Findings of the Association for Computational Linguistics: EMNLP 2023, 2023, Página(s) pages 11031–11042, ISBN 979-8-89176-061-5
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-emnlp.736

Språk(teknologi) är nyckeln till intelligens och rättvisa

Autores: Jörg Tiedemann
Publicado en: 2022, ISSN 0358-9293
Editor: Språkbruk

Democratizing neural machine translation with OPUS-MT

Autores: Tiedemann J.; Aulamo M.; Bakshandaeva D.; Boggia M.; Grönroos S. A.; Nieminen T.; Raganato A.; Scherrer Y.; Vázquez R.; Virpioja S.
Publicado en: Language Resources and Evaluation, Edición 50, 2023, ISSN 1574-020X
Editor: Springer Verlag
DOI: 10.1007/s10579-023-09704-w

A Systematic Study of Inner-Attention-Based Sentence Representations in Multilingual Neural Machine Translation

Autores: Raúl Vázquez, Alessandro Raganato, Mathias Creutz, Jörg Tiedemann
Publicado en: Computational Linguistics, Edición 46/2, 2020, Página(s) 387-424, ISSN 0891-2017
Editor: MIT Press
DOI: 10.1162/coli_a_00377

Are Multilingual Neural Machine Translation Models Better at Capturing Linguistic Features?

Autores: David Mareček, Hande Celikkanat, Miikka Silfverberg, Vinit Ravishankar, Jörg Tiedemann
Publicado en: Prague Bulletin of Mathematical Linguistics, Edición 115/1, 2020, Página(s) 143-162, ISSN 1804-0462
Editor: Institute of Formal and Applied Linguistics, Charles University
DOI: 10.14712/00326585.009

Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

Autores: Stig-Arne Gronroos, Sami Virpioja, Mikko Kurimo
Publicado en: Machine Translation, Edición 34, 2021, Página(s) 251-286, ISSN 0922-6567
Editor: Kluwer Academic Publishers
DOI: 10.1007/s10590-020-09253-x

What Do Language Representations Really Represent?

Autores: Johannes Bjerva, Robert Östling, Maria Han Veiga, Jörg Tiedemann, Isabelle Augenstein
Publicado en: Computational Linguistics, Edición 45/2, 2019, Página(s) 381-389, ISSN 0891-2017
Editor: MIT Press
DOI: 10.1162/coli_a_00351

Neural morphosyntactic tagging for Rusyn

Autores: Yves Scherrer, Achim Rabus
Publicado en: Natural Language Engineering, Edición 25/5, 2019, Página(s) 633-650, ISSN 1351-3249
Editor: Cambridge University Press
DOI: 10.1017/s1351324919000287

Digitising Swiss German: how to process and study a polycentric spoken language

Autores: Yves Scherrer, Tanja Samardžić, Elvira Glaser
Publicado en: Language Resources and Evaluation, Edición 53/4, 2019, Página(s) 735-769, ISSN 1574-020X
Editor: Springer Verlag
DOI: 10.1007/s10579-019-09457-5

Sentence Embeddings in NLI with Iterative Refinement Encoders

Autores: Aarne Johannes Talman, Anssi Yli-Jyrä, Jörg Tiedemann
Publicado en: Natural Language Engineering, 2019, Página(s) 467-482, ISSN 1351-3249
Editor: Cambridge University Press

A Finnish news corpus for named entity recognition

Autores: Teemu Ruokolainen, Pekka Kauppinen, Miikka Silfverberg, Krister Lindén
Publicado en: Language Resources and Evaluation, Edición 54/1, 2020, Página(s) 247-272, ISSN 1574-020X
Editor: Springer Verlag
DOI: 10.1007/s10579-019-09471-7

How to Dissect a Muppet: The Structure of Transformer Embedding Spaces

Autores: Timothee Mickus, Denis Paperno, Mathieu Constant
Publicado en: How to Dissect a Muppet: The Structure of Transformer Embedding Spaces, 2022, ISSN 2307-387X
Editor: Transactions of the Association for Computational Linguistics (TACL)
DOI: 10.1162/tacl_a_00501

Advances in subword-based HMM-DNN speech recognition across languages

Autores: Peter Smit, Sami Virpioja, Mikko Kurimo
Publicado en: Computer Speech & Language, Edición 66, 2021, Página(s) 101158, ISSN 0885-2308
Editor: Academic Press
DOI: 10.1016/j.csl.2020.101158

Idiosyncratic frequency as a measure of derivation vs. inflection

Autores: Maria Copot, Timothee Mickus, Olivier Bonami
Publicado en: Journal of Language Modeling, 2023, ISSN 2299-8470
Editor: Online
DOI: 10.15398/jlm.v10i2.301

Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses

Autores: Aina Gari Soler, Marianna Apidianaki
Publicado en: Transactions of the Association for Computational Linguistics (TACL), 2021, Página(s) 825-844, ISSN 2307-387X
Editor: Transactions of the Association for Computational Linguistics (TACL)

European Language Grid : A Language Technology Platform for Multilingual Europe: Open Translation Models, Tools and Services

Autores: Jörg Tiedemann, Mikko Aulamo, Sam Hardwick, Tommi Nieminen
Publicado en: Cognitive Technologies, 2022
Editor: Springer

Found in Translation – Natural Language Understanding with Cross-Lingual Grounding

Publicaciones

Compartir esta página Compartir esta página en las redes sociales

Descargar Descargar el contenido de la página