DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 25

1
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach ...
BASE
Show details
2
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach
Sánchez-Cartagena, Víctor M.; Sánchez-Martínez, Felipe; Pérez-Ortiz, Juan Antonio. - : Association for Computational Linguistics, 2021
BASE
Show details
3
Presentació del monogràfic «Spoken Corpus Linguistics in Romance: thoughts, design and results» ; Presentation of the monograph «Spoken Corpus Linguistics in Romance: thoughts, design and results»
In: Caplletra. Revista Internacional de Filologia.; Caplletra 69 (tardor 2020); 117-123 ; Caplletra. Revista Internacional de Filologia; Caplletra 69 (tardor 2020); 117-123 ; 2386-7159 ; 0214-8188 (2020)
BASE
Show details
4
Reading comprehension of machine translation output: what makes for a better read?
In: Castilho, Sheila orcid:0000-0002-8416-6555 and Guerberof Arenas, Ana orcid:0000-0001-9820-7074 (2018) Reading comprehension of machine translation output: what makes for a better read? In: 21st Annual Conference of the European for Machine Translation, 28-30 May 2018, Alacant/Alicante, Spain. ISBN 978-84-09-01901-4 (2018)
BASE
Show details
5
ParaCrawl Corpus version 1.0
BASE
Show details
6
Predicting insertion positions in word-level machine translation quality estimation
BASE
Show details
7
Towards Optimizing MT for Post-Editing Effort: Can BLEU Still Be Useful?
BASE
Show details
8
Assisting non-expert speakers of under-resourced languages in assigning stems and inflectional paradigms to new word entries of morphological dictionaries
Forcada, Mikel L.; Carrasco, Rafael C.; Pérez-Ortiz, Juan Antonio. - : Springer Science+Business Media Dordrecht, 2017
BASE
Show details
9
Towards Optimizing MT for Post-Editing Effort: Can BLEU Still Be Useful?
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 183-195 (2017) (2017)
Abstract: We propose a simple, linear-combination automatic evaluation measure (AEM) to approximate post-editing (PE) effort. Effort is measured both as PE time and as the number of PE operations performed. The ultimate goal is to define an AEM that can be used to optimize machine translation (MT) systems to minimize PE effort, but without having to perform unfeasible repeated PE during optimization. As PE effort is expected to be an extensive magnitude (i.e., one growing linearly with the sentence length and which may be simply added to represent the effort for a set of sentences), we use a linear combination of extensive and pseudo-extensive features. One such pseudo-extensive feature, 1–BLEU times the length of the reference, proves to be almost as good a predictor of PE effort as the best combination of extensive features. Surprisingly, effort predictors computed using independently obtained reference translations perform reasonably close to those using actual post-edited references. In the early stage of this research and given the inherent complexity of carrying out experiments with professional post-editors, we decided to carry out an automatic evaluation of the AEMs proposed rather than a manual evaluation to measure the effort needed to post-edit the output of an MT system tuned on these AEMs. The results obtained seem to support current tuning practice using BLEU, yet pointing at some limitations. Apart from this intrinsic evaluation, an extrinsic evaluation was also carried out in which the AEMs proposed were used to build synthetic training corpora for MT quality estimation, with results comparable to those obtained when training with measured PE efforts.
Keyword: Computational linguistics. Natural language processing; P98-98.5
URL: https://doi.org/10.1515/pralin-2017-0019
https://doaj.org/article/40f7759398754624ae8baf6dca0dbad5
BASE
Hide details
10
New directions in empirical translation process research exploring the CRITT TPR-DB : Springer International Publishing, Switzerland, 2016, ISBN: 978-3-319-20357-7, v + 315 pp. [<Journal>]
Esplà-Gomis, Miquel [Verfasser]
DNB Subject Category Language
Show details
11
Serbian-English parallel corpus srenWaC 1.0
Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016
BASE
Show details
12
Finnish-English parallel corpus fienWaC 1.0
Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016
BASE
Show details
13
Tourism English-Croatian Parallel Corpus 2.0
Toral, Antonio; Esplà-Gomis, Miquel; Klubička, Filip. - : Abu-MaTran project, 2016
BASE
Show details
14
Croatian-English parallel corpus hrenWaC 2.0
Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016
BASE
Show details
15
Slovene-English parallel corpus slenWaC 1.0
Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016
BASE
Show details
16
Using external sources of bilingual information for word-level quality estimation in translation technologies
Esplà-Gomis, Miquel. - : Universidad de Alicante, 2016
BASE
Show details
17
Using Machine Translation to Provide Target-Language Edit Hints in Computer Aided Translation Based on Translation Memories
BASE
Show details
18
Using external sources of bilingual information for on-the-fly word alignment ...
BASE
Show details
19
Using external sources of bilingual information for on-the-fly word alignment
BASE
Show details
20
A simple approach to use bilingual information sources for word alignment ; Una manera sencilla para usar fuentes de información bilingüe para el alineamiento de palabras
Esplà-Gomis, Miquel; Sánchez-Martínez, Felipe; Forcada, Mikel L.. - : Sociedad Española para el Procesamiento del Lenguaje Natural, 2012
BASE
Show details

Page: 1 2

Catalogues
0
0
1
0
1
0
0
Bibliographies
1
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
23
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern