Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Toral Ruiz A."'
Autor:
Sarti, Gabriele, Bisazza, Arianna, Guerberof, Ana, Toral Ruiz, Antonio, Goldberg, Yoav, Kozareva, Zornitsa, Zhang, Yue
Publikováno v:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 7795-7816
STARTPAGE=7795;ENDPAGE=7816;TITLE=Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
STARTPAGE=7795;ENDPAGE=7816;TITLE=Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::5a9b5f69aacfed83bc1637016e180726
https://research.rug.nl/en/publications/2ceb7554-3290-4063-9a45-3fa8b300ca83
https://research.rug.nl/en/publications/2ceb7554-3290-4063-9a45-3fa8b300ca83
Autor:
Guerberof, Ana, Toral Ruiz, Antonio, Moniz, Helena, Macken, Lieve, Rufener, Andrew, Barrault, Loïc, Costa-jussà, Marta R., Declercq, Christophe, Koponen, Maarit, Kemp, Ellie, Pilos, Spyridon, Forcada, Mikel L., Scarton, Carolina, van den Bogaert, Joachim, Daems, Joke, Tezcan, Arda, Vanroy, Bram, Fonteyne, Margot
Publikováno v:
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, 357-358
STARTPAGE=357;ENDPAGE=358;TITLE=Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
STARTPAGE=357;ENDPAGE=358;TITLE=Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
We present here the EU-funded project CREAMT that seeks to understand what is meant by creativity in different translation modalities, e.g. machine translation, post-editing or professional translation. Focusing on the textual elements that determine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::94e2dc9bde031b5c7ae5de41695bc1f9
https://research.rug.nl/en/publications/70fa4f36-5292-45b7-814e-c47f89db38d6
https://research.rug.nl/en/publications/70fa4f36-5292-45b7-814e-c47f89db38d6
Autor:
Toral Ruiz, Antonio, Caselli, Tommaso
La lingüística computacional (LC) es un campo interdisciplinar en el que se encuentran la inteligencia artificial, la lingüística, la ciencia cognitiva y la informática, dedicado al estudio del lenguaje natural desde una perspectiva computaciona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d15b38d71edd353bf3e9447c4b3b90d
Autor:
Toral Ruiz, Antonio, Caselli, Tommaso
Computational Linguistics (CL) is an interdisciplinary field at the intersection of Artificial Intelligence, Linguistics, Cognitive Science, and Computer Science, devoted to the study of natural language from a computational perspective. The main the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5990332caf5957eb9fa99fc6849a9617
Autor:
Lai, Huiyuan, Mao, Jiali, Toral Ruiz, Antonio, Nissim, Malvina, Belz, Anya, Popović, Maja, Reiter, Ehud, Shimorina, Anastasia
Publikováno v:
Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval), 102-115
STARTPAGE=102;ENDPAGE=115;TITLE=Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval)
STARTPAGE=102;ENDPAGE=115;TITLE=Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval)
Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement.
Autor:
Edman, Lukas, Toral Ruiz, Antonio, van Noord, Gertjan, Bandyopadhyay, Sivaji, Devi, Sobha Lalitha, Bhattacharyya, Pushpak
Publikováno v:
Proceedings of the 18th International Conference on Natural Language Processing (ICON), 86-92
STARTPAGE=86;ENDPAGE=92;TITLE=Proceedings of the 18th International Conference on Natural Language Processing (ICON)
STARTPAGE=86;ENDPAGE=92;TITLE=Proceedings of the 18th International Conference on Natural Language Processing (ICON)
This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available. We find that, in very low-resource scenarios, statistical n-gram language models outperform state-of-the-art neural models. Our
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::255111e6a9a75afea4da03afc825c712
https://research.rug.nl/en/publications/f6ed7384-8c3c-4914-a771-ae3a5ad6dfd5
https://research.rug.nl/en/publications/f6ed7384-8c3c-4914-a771-ae3a5ad6dfd5
Autor:
Lai, Huiyuan, Toral Ruiz, Antonio, Nissim, Malvina, Zong, Chengqing, Xia, Fei, Li, Wenjie, Navigli, Roberto
Publikováno v:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2, 484-494
University of Groningen
ACL/IJCNLP (2)
University of Groningen
ACL/IJCNLP (2)
Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to-sequence (BART) models boosts content preservation, and that this is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4276577acd943dbc62610b8f367ec4a
http://arxiv.org/abs/2105.06947
http://arxiv.org/abs/2105.06947
Autor:
Edman, Lukas, Toral Ruiz, Antonio, Noord, van, Gertjan, Martins, André, Moniz, Helena, Fumega, Sara, Martins, Bruno, Batista, Fernando, Coheur, Luisa, Parra, Carla, Trancoso, Isabel, Turchi, Marco, Bisazza, Arianna, Moorkens, Joss, Guerberof, Ana, Nurminen, Mary, Marg, Lena, Forcada, Mikel L.
Publikováno v:
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 81-90
STARTPAGE=81;ENDPAGE=90;TITLE=Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
STARTPAGE=81;ENDPAGE=90;TITLE=Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
Unsupervised Machine Translation hasbeen advancing our ability to translatewithout parallel data, but state-of-the-artmethods assume an abundance of mono-lingual data. This paper investigates thescenario where monolingual data is lim-ited as well, fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::fe29a88937a2ab08d283d04cfc727379
https://research.rug.nl/en/publications/680bb044-42d6-4f27-9a25-236912b32c17
https://research.rug.nl/en/publications/680bb044-42d6-4f27-9a25-236912b32c17
Publikováno v:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, 1063-1073
STARTPAGE=1063;ENDPAGE=1073;TITLE=Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
STARTPAGE=1063;ENDPAGE=1073;TITLE=Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::33e2111ebedd0698b378ac276ac0f8fa
https://research.rug.nl/en/publications/f09c041c-dbea-4ae4-be20-43b5f6d6f341
https://research.rug.nl/en/publications/f09c041c-dbea-4ae4-be20-43b5f6d6f341
Autor:
Ruimy N., Toral Ruiz A.
Publikováno v:
LREC 2008, Sixth International Conference on Language Resources and Evaluation, pp. 3555–3560, Marrakech, Marocco, 26/05-01/06/2008
info:cnr-pdr/source/autori:Ruimy N.; Toral Ruiz A./congresso_nome:LREC 2008, Sixth International Conference on Language Resources and Evaluation/congresso_luogo:Marrakech, Marocco/congresso_data:26%2F05-01%2F06%2F2008/anno:2008/pagina_da:3555/pagina_a:3560/intervallo_pagine:3555–3560
info:cnr-pdr/source/autori:Ruimy N.; Toral Ruiz A./congresso_nome:LREC 2008, Sixth International Conference on Language Resources and Evaluation/congresso_luogo:Marrakech, Marocco/congresso_data:26%2F05-01%2F06%2F2008/anno:2008/pagina_da:3555/pagina_a:3560/intervallo_pagine:3555–3560
Notwithstanding its acknowledged richness, the SIMPLE semantic model does not offer the representational vocabulary for encoding some conceptual links holding between events and their participants and among co-participants in events. Although critica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=cnr_________::eda9c28a3f4147134e817173bd7dc833
https://publications.cnr.it/doc/84721
https://publications.cnr.it/doc/84721