Home Catalogue search

eng

Refine your search:

Search in the Catalogues and Directories






	Sort by
Simple Search

Hits 1 – 11 of 11

1	Joint WMT 2012 Submission of the QUAERO Project
	Le, Hai-son; Lavergne, Thomas; Freitag, Markus. - : Association for Computational Linguistics, 2022
	BASE
	Show details

2	Joint WMT Submission of the QUAERO Project
	Ney, Hermann; Senellart, Jean; Crego, Josep Maria. - : Association for Computational Linguistics, 2022
	BASE
	Show details

3	Revisiting Multi-Domain Machine Translation
	Pham, Minh Quang; Crego, Josep-Maria; Yvon, François
	In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03159744 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2021, 9, pp.17-35. ⟨10.1162/tacl_a_00351⟩ (2021)
	BASE
	Show details

4	Revisiting Multi-Domain Machine Translation
	Pham, Minh Quang; Crego, Josep-Maria; Yvon, François
	In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03159743 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2021, 9, pp.17-35 (2021)
	BASE
	Show details

5	Boosting Neural Machine Translation with Similar Translations
	Xu, Jitao; Crego, Josep-Maria; Senellart, Jean
	In: Annual Meeting of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02956324 ; Annual Meeting of the Association for Computational Linguistics, Jul 2020, Seattle, United States. pp.1570-1579, ⟨10.18653/v1/2020.acl-main.143⟩ (2020)
	Abstract: International audience ; This paper explores data augmentation methods for training Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches. In particular, we show how we can simply feed the neural model with information on both source and target sides of the fuzzy matches, we also extend the similarity to include semantically related translations retrieved using distributed sentence representations. We show that translations based on fuzzy matching provide the model with "copy" information while translations based on embedding similarities tend to extend the translation "context". Results indicate that the effect from both similar sentences are adding up to further boost accuracy, are combining naturally with model fine-tuning and are providing dynamic adaptation for unseen translation pairs. Tests on multiple data sets and domains show consistent accuracy improvements. To foster research around these techniques, we also release an Open-Source toolkit with efficient and flexible fuzzy-match implementation.
	Keyword: [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO]Computer Science [cs]; Fuzzy Match; Neural Machine Translation; Translation Memory
	URL: https://doi.org/10.18653/v1/2020.acl-main.143 https://hal.archives-ouvertes.fr/hal-02956324/file/2020.acl-main.144.pdf https://hal.archives-ouvertes.fr/hal-02956324 https://hal.archives-ouvertes.fr/hal-02956324/document
	BASE
	Hide details

6	Generic and Specialized Word Embeddings for Multi-Domain Machine Translation
	Pham, Minh Quang; Crego, Josep-Maria; Yvon, François...
	In: International Workshop on Spoken Language Translation ; https://hal.archives-ouvertes.fr/hal-02343215 ; International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China. ⟨10.5281/zenodo.3524978⟩ ; https://zenodo.org/communities/iwslt2019/ (2019)
	BASE
	Show details

7	Fixing Translation Divergences in Parallel Corpora for Neural MT
	Pham, Minh Quang; Crego, Josep-Maria; Senellart, Jean...
	In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing ; Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-01908309 ; Conference on Empirical Methods in Natural Language Processing, Nov 2018, Bruxelles, Belgium. pp.2967 - 2973 (2018)
	BASE
	Show details

8	A multilingual corpus of tweets for domain adaptation
	Gilles, Adda; Crego, Josep-Maria; Lacroix, Ophélie...
	In: https://hal.archives-ouvertes.fr/hal-01529857 ; [Research Report] LIMSI-CNRS; ELDA; Systran. 2017 (2017)
	BASE
	Show details

9	N-code: an open-source Bilingual N-gram SMT Toolkit
	Crego, Josep-Maria; Yvon, François; Mariño, José B.
	In: ISSN: 1804-0462 ; The Prague Bulletin of Mathematical Linguistics ; https://hal.archives-ouvertes.fr/hal-01960706 ; The Prague Bulletin of Mathematical Linguistics, Univerzita Karlova v Praze, 2011, 96, pp.49-58 (2011)
	BASE
	Show details

10	Improving statistical MT by coupling reordering and decoding
	Crego, Josep Maria; Mariño, José B.
	In: Machine translation. - Dordrecht [u.a.] : Springer Science + Business Media 20 (2007) 3, 199-215
	OLC Linguistik
	Show details

11	Discriminative Alignment Training without Annotated Data for Machine Translation
	Lambert, Patrik; Banchs, Rafael,; Crego, Josep-Maria
	In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers ; Conference of the North American Chapter of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-00430864 ; Conference of the North American Chapter of the Association for Computational Linguistics, Apr 2007, United States. pp.85-88 (2007)
	BASE
	Show details

© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern