Results 1 to 10 of about 1,607,695 (289)

Automatic testing and improvement of machine translation [PDF]

open access: yesProceedings of the ACM/IEEE 42nd International Conference on Software Engineering, 2020
This paper presents TransRepair, a fully automatic approach for testing and repairing the consistency of machine translation systems. TransRepair combines mutation with metamorphic testing to detect inconsistency bugs (without access to human oracles).
Zeyu Sun 0004   +4 more
openaire   +3 more sources

Neural Machine Translation

open access: yesRevista Tradumàtica, 2017
From the outset, automatic translation was dominated by systems based on linguistic information, but then later other approaches opened up the way, such as translation memories and statistical machine translation which draw on parallel language corpora ...
Francisco Casacuberta Nolla   +1 more
doaj   +1 more source

Désambiguïsation des sens du prédicat adjectival farouche dans le cadre d’une approche orientée objets

open access: yesNeophilologica, 2011
This article examines the French adjective farouche with the aim of disambiguating all its meanings. The methodology of this study is based on the object-oriented approach proposed by W. Banyś.
Michał Hrabia
doaj   +1 more source

Automatic detection of omissions in translations [PDF]

open access: yesProceedings of the 16th conference on Computational linguistics -, 1996
6 pages, minor revisions on Sept.
openaire   +4 more sources

Automatic translation of noun compounds [PDF]

open access: yesProceedings of the 14th conference on Computational linguistics -, 1992
This paper describes the treatment of nominal compounds in a tranarer based machine translation system; it presents a new approach for resolving ambiguities in compound segmentation and Constituent structure selection using a combination of linguistic rules and statistical data.
Ulrike Rackow, Ido Dagan, Ulrike Schwall
openaire   +2 more sources

Contextualized Translation of Automatically Segmented Speech [PDF]

open access: yesInterspeech 2020, 2020
Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not syntax-informed, the resulting segments do not necessarily correspond to well-formed sentences uttered by the speaker but,
Marco Gaido   +4 more
openaire   +4 more sources

Software translation specifics and partial automation

open access: yesLietuvos Matematikos Rinkinys, 2004
There is analysis of software translation specifics and possibilities of partial automatic translation, pre­sented in this paper. Referencing on statistical text analysis the efficiency of automated translation tools application is estimated.
Rimgaudas Laucius
doaj   +3 more sources

Question de métonymie dans la traduction automatique

open access: yesNeophilologica, 2011
The article is devoted to the problem of metonymy in automatic translation. The author focuses on possible difficulties that can arise in the process of automatic translation of metonymic structures.
Anna Czekaj
doaj   +1 more source

Question Embeddings Based on Shannon Entropy. Solving intent classification task in goal-oriented dialogue system

open access: yesProceedings of the International Conference on Applied Innovations in IT, 2019
Question-answering systems and voice assistants are becoming major part of client service departments of many organizations, helping them to reduce the labor costs of staff. In many such systems, there is always natural language understanding module that
Aleksandr Perevalov   +3 more
doaj   +1 more source

Classement de métonymies et traduction automatique

open access: yesNeophilologica, 2020
The paper is a continuation of the author’s previous work regarding the legitimacy of metonymy classification for the needs of automatic translation. The author attempts to solve the problem presented in the paper entitled Classification of metonymy and
Anna Czekaj
doaj   +1 more source

Home - About - Disclaimer - Privacy