Results 31 to 40 of about 64,639 (121)
Simplifying drug package leaflets written in Spanish by using word embedding
Background Drug Package Leaflets (DPLs) provide information for patients on how to safely use medicines. Pharmaceutical companies are responsible for producing these documents.
Isabel Segura-Bedmar, Paloma Martínez
doaj +1 more source
Wiki-Translator: Multilingual Experiments for In-Domain Translations [PDF]
The benefits of using comparable corpora for improving translation quality for statistical machine translators have been already shown by various researchers.
Dan Tufis +2 more
doaj
Using collocation segmentation to augment the phrase table [PDF]
This paper describes the 2010 phrase-based statistical machine translation system developed at the TALP Research Center of the UPC1 in cooperation with BMIC2 and VMU3. In phrase-based SMT, the phrase table is the main tool in translation.
Banchs Martínez, Rafael Enrique +4 more
core
Metaphern in Zeiten der Wirtschaftskrise
The reports of official economic institutions were especially relevant for society during the world economic crisis because they conveyed reliable information about the financial situation.
Carmen Mateo Gallego +1 more
doaj
Tracking relevant alignment characteristics for machine translation [PDF]
In most statistical machine translation (SMT) systems, bilingual segments are extracted via word alignment. In this paper we compare alignments tuned directly according to alignment F-score and BLEU score in order to investigate the alignment ...
Lambert, Patrik +3 more
core +3 more sources
Fictional dialogues, termed prefabricated orality, involve the use of features often associated with spoken language, and discourse markers are frequent markers of orality that pose a challenge for translators due to their multifunctionality.
Olaia Andaluz-Pinedo
doaj +1 more source
Neural machine translation using bitmap fonts [PDF]
Recently, translation systems based on neural networks are starting to compete with systems based on phrases. The systems which are based on neural networks use vectorial repre- sentations of words.
Aldón Mínguez, David +2 more
core
Termhood-based Comparability Metrics of Comparable Corpus in Special Domain
Cross-Language Information Retrieval (CLIR) and machine translation (MT) resources, such as dictionaries and parallel corpora, are scarce and hard to come by for special domains.
C.Y. Kit, T. Talvensaari, T. Talvensaari
core +1 more source
Evaluating syntax-driven approaches to phrase extraction for MT [PDF]
In this paper, we examine a number of different phrase segmentation approaches for Machine Translation and how they perform when used to supplement the translation model of a phrase-based SMT system. This work represents a summary of a number of years of
Groves, Declan +3 more
core
Tied Multitask Learning for Neural Speech Translation
We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task, since higher-level
Anastasopoulos, Antonios, Chiang, David
core +1 more source

