Zobrazeno 1 - 10 of 13 pro vyhledávání: '"Eva Vanmassenhove"'
2
A Case Study of Natural Gender Phenomena in Translation. A Comparison of Google Translate, Bing Microsoft Translator and DeepL for English to Italian, French and Spanish
Autor: Andy Way, Argentina Anna Rescigno, Johanna Monti, Eva Vanmassenhove
Publikováno v: A Case Study of Natural Gender Phenomena in Translation: A Comparison of Google Translate, Bing {M}icrosoft Translator and DeepL for English to Italian, French and Spanish
This paper presents the results of an evaluation of Google Translate, DeepL and Bing Microsoft Translator with reference to natural gender translation and provides statistics about the frequency of female, male and neutral forms in the translations o
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ddaab37785775229d2f290be9742c6ea
http://books.openedition.org/aaccademia/8844
Zobrazit plný text záznamu
3
A Comparison of Different NMT Approaches to Low-Resource Dutch-Albanian Machine Translation
Autor: Arbnor Rama, Eva Vanmassenhove
Publikováno v: Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021): LoResMT2021, 68-77
ISSUE=4;STARTPAGE=68;ENDPAGE=77;TITLE=Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)
Tilburg University-PURE
Low-resource languages can be understood as languages that are more scarce, less studied, less privileged, less commonly taught and for which there are less resources available (Singh, 2008; Cieri et al., 2016; Magueresse et al., 2020). Natural Langu
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0f5330dc4bb30aba8b9888c0b6824713
https://research.tilburguniversity.edu/en/publications/e9a550fc-0b2c-40a2-9678-379eeff4ace7
Zobrazit plný text záznamu
4
Generating Gender Augmented Data for NLP
Autor: Maja Popović, Eva Vanmassenhove, Declan Groves, Nishtha Jain
Publikováno v: STARTPAGE=93;ENDPAGE=102;TITLE=3th Workshop on Gender Bias in Natural Language Processing
Gender bias is a frequent occurrence in NLP-based applications, especially pronounced in gender-inflected languages. Bias can appear through associations of certain adjectives and animate nouns with the natural gender of referents, but also due to un
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::226ef0b583182a7495484c9a14d4dbe7
Zobrazit plný text záznamu
5
Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation
Autor: Dimitar Shterionov, Matthew Gwilliam, Eva Vanmassenhove
Publikováno v: EACL
EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, 2203-2213
STARTPAGE=2203;ENDPAGE=2213;TITLE=EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Recent studies in the field of Machine Translation (MT) and Natural Language Processing (NLP) have shown that existing models amplify biases observed in the training data. The amplification of biases in language technology has mainly been examined wi
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8ba05dc8cccd8b0defaeaa969793587d
https://doi.org/10.18653/v1/2021.eacl-main.188
Zobrazit plný text záznamu
6
Getting Gender Right in Neural Machine Translation
Autor: Christian Hardmeier, Eva Vanmassenhove, Andy Way
Publikováno v: Vanmassenhove, Eva ORCID: 0000-0003-1162-820X , Hardmeier, Christian and Way, Andy ORCID: 0000-0001-5736-5930 (2018) Getting gender right in neural machine translation. In: 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP2018), 30 Oct-4 Nov 2018, Brussels, Belgium.
Scopus-Elsevier
Vanmassenhove, E, Hardmeier, C & Way, A 2018, Getting Gender Right in Neural Machine Translation . in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing . Brussels, Belgium, pp. 3003-3008, 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31/10/18 . https://doi.org/10.18653/v1/D18-1334
Speakers of different languages must attend to and encode strikingly different aspects of the world in order to use their language correctly (Sapir, 1921; Slobin, 1996). One such difference is related to the way gender is expressed in a language. Say
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ed79252ada0c326651a5ab09c08ee726
Zobrazit plný text záznamu
7
Europarl Datasets with Demographic Speaker Information
Autor: Eva Vanmassenhove, Hardmeier, C.
Publikováno v: RUA. Repositorio Institucional de la Universidad de Alicante
Universidad de Alicante (UA)
Scopus-Elsevier
Research on speaker-adapted neural machine translation (NMT) is scarce. One of the main challenges for more personalized MT systems is finding large enough annotated parallel datasets with speaker information. Rabinovich et al. (2017) published an an
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::65c4106ab5e309789b1cf4cd7c2dd00d
http://hdl.handle.net/10045/76104
Zobrazit plný text záznamu
8
ABI neural ensemble model for gender prediction adapt Bar-ilan submission for the Clin29 shared task on gender prediction
Autor: Eva Vanmassenhove, Amit Moryossef, Alberto Poncelas, Andy Way, Dimitar Shterionov
Publikováno v: Tilburg University-PURE
Scopus-Elsevier
We present our system for the CLIN29 shared task on cross-genre gender detection for Dutch. We experimented with a multitude of neural models (CNN, RNN, LSTM, etc.), more "traditional" models (SVM, RF, LogReg, etc.), different feature sets as well as
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3570ba5fab7506d6f2adf333a3c04fd8
https://research.tilburguniversity.edu/en/publications/3cdc2364-fa65-45fa-a953-3bed6554277d
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje