Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses

Autor: Joel Tetreault, Maria Nadejde, Courtney Napoles

Publikováno v: Transactions of the Association for Computational Linguistics, Vol 7, Pp 551-566 (2019)

Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b51874f3d0145190abcf2e9d56865994
https://doi.org/10.1162/tacl_a_00282

Nematus: a Toolkit for Neural Machine Translation

Autor: Alexandra Birch, Marcin Junczys-Dowmunt, Samuel Läubli, Barry Haddow, Kyunghyun Cho, Julian Hitschler, Antonio Valerio Miceli Barone, Maria Nadejde, Rico Sennrich, Jozef Mokry, Orhan Firat

Publikováno v: Sennrich, R, Firat, O, Cho, K, Birch-Mayne, A, Haddow, B, Hitschler, J, Junczys-Dowmunt, M, Läubli, S, Miceli Barone, A V, Mokry, J & Nadejde, M 2017, Nematus: a Toolkit for Neural Machine Translation . in Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics . Valencia, Spain, pp. 65-68, 15th EACL 2017 Software Demonstrations, Valencia, Spain, 3/04/17 . https://doi.org/10.18653/v1/E17-3017
Sennrich, R, Firat, O, Cho, K, Birch-Mayne, A, Haddow, B, Hitschler, J, Junczys-Dowmunt, M, Läubli, S, Miceli Barone, A, Mokry, J & Nadejde, M 2017, Nematus: a Toolkit for Neural Machine Translation . in Proceedings of the EACL 2017 Software Demonstrations . Association for Computational Linguistics (ACL), pp. 65-68 .
Sennrich, Rico; Firat, Orhan; Cho, Kyunghyun; Birch, Alexandra; Haddow, Barry; Hitschler, Julian; Junczys-Dowmunt, Marcin; Läubli, Samuel; Miceli Barone, Antonio Valerio; Mokry, Jozef; Nadejde, Maria (2017). Nematus: a Toolkit for Neural Machine Translation. In: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, 3 April 2017-7 April 2017, 65-68.
Zurich Open Repository and Archive
Edinburgh Research Explorer
arXiv.org e-Print Archive
EACL (Software Demonstrations)
Scopus-Elsevier

We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a2e1a64953f6ec2cbeebd30503b1984
https://hdl.handle.net/20.500.11820/115cdfe3-231e-4c87-929e-e55787916b26

Modeling Selectional Preferences of Verbs and Nouns in String-to-Tree Machine Translation

Autor: Philipp Koehn, Maria Nadejde, Alexandra Birch

Publikováno v: Nadejde, M, Birch, A & Koehn, P 2016, Modeling Selectional Preferences of Verbs and Nouns in String-to-Tree Machine Translation . in Proceedings of the First Conference on Machine Translation, Volume 1: Research Papers . Berlin, Germany, pp. 32-42, First Conference on Machine Translation, Berlin, Germany, 11/08/16 . https://doi.org/10.18653/v1/W16-2204
Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers
WMT
Stroudsburg, PA : Association for Computational Linguistics 32-42 (2016). doi:10.18653/v1/W16-2204
The 54th Annual Meeting of the Association for Computational Linguistics-proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016.-Volume 1, Research Papers
The 54th Annual Meeting of the Association for Computational Linguistics-proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016.-Volume 1, Research Papers1. Conference on Machine Translation, WMT16, Berlin, Germany, 2016-08-11-2016-08-12

We address the problem of mistranslated predicate-argument structures in syntax based machine translation. This paper explores whether knowledge about semantic affinities between the target predicates and their argument fillers is useful for translat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::025888107351aef8d6f434f1b3037d49
https://hdl.handle.net/20.500.11820/5d65c3a2-4f68-4fa4-a344-32ac71fc07c5

Edinburgh's Syntax-Based Systems at WMT 2015

Autor: Philipp Koehn, Matthias Huck, Rico Sennrich, Eva Hasler, Maria Nadejde, Philip Williams

Publikováno v: Proceedings of the Tenth Workshop on Statistical Machine Translation
WMT@EMNLP
Red Hook, NY : Curran 199-209 (2015). doi:10.18653/v1/W15-3024
Williams, P, Sennrich, R, Nadejde, M, Huck, M & Koehn, P 2015, Edinburgh's Syntax-Based Systems at WMT 2015 . in Proceedings of the Tenth Workshop on Statistical Machine Translation . Lisbon, Portugal, pp. 199-209 . < http://aclweb.org/anthology/W15-3024 >

This paper describes the string-to-tree systems built at the University of Edinburgh for the WMT 2014 shared translation task. We developed systems for English-German, Czech-English, FrenchEnglish, German-English, Hindi-English, and Russian-English.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d5829717e5b28ddb26b6109fbc8ff0ef