Exploració per autor "Ruiz Costa-Jussà, Marta"
Ara es mostren els items 82-101 de 135
-
Measuring the mixing of contextual information in the transformer
Ferrando Monsonís, Javier; Gallego Olsina, Gerard Ion; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2022)
Comunicació de congrés
Accés obertThe Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works have ... -
Modelo estocástico de traducción basado en N-gramas de tuplas bilingues y combinación log-lineal de características
Mariño, José B.; Banchs, Rafael E.; Crego, Josep Maria; de Gispert, Adrià; Lambert, Patrik; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (2005-09-01)
Article
Accés restringit per política de l'editorialEn esta comunicación se presenta un sistema de traducción estocástica basado en el modelado mediante N-gramas de la probabilidad conjunta de textos bilingües. La unidad básica del modelo es la tupla, par de cadenas de ... -
Moses-based official baseline for NEWS 2016
Ruiz Costa-Jussà, Marta (2016)
Text en actes de congrés
Accés obertTransliteration is the phonetic translation between two different languages. There are many works that approach transliteration using machine translation methods. This paper describes the official baseline system for the ... -
Multilingual and interlingual semantic representations for natural language processing: a brief introduction
Ruiz Costa-Jussà, Marta; España-Bonet, Cristina; Fung, Pascale; Smith, Noah (2020)
Article
Accés obertWe introduce the Computational Linguistics special issue on Multilingual and Interlingual Semantic Representations for Natural Language Processing. We situate the special issue’s five articles in the context of our ... -
Multilingual machine translation: Closing the gap between shared and language-specific encoder-decoders
Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián; Artetxe Zurutuza, Mikel (Association for Computational Linguistics, 2021)
Comunicació de congrés
Accés obertState-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on ... -
Multilingual machine translation: Deep analysis of language-specific encoder-decoders
Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2022-04-25)
Article
Accés obertState-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new ... -
Multilingual natural language processing: Towards universal translation
Ruiz Costa-Jussà, Marta (Springer Nature, 2021-05)
Article
Accés obertState of the art neural network approaches enable massive multilingual translation. How close are we to universal translation in any language? -
Multilingual neural machine translation: case-study for Catalan, Spanish and Portuguese romance languages
Vergés Boncompte, Pere; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2020)
Comunicació de congrés
Accés obertIn this paper, we describe the TALP-UPC participation in the WMT Similar Language Translation task between Catalan, Spanish, and Portuguese, all of them, Romance languages. We made use of different techniques to improve ... -
Multilingual, multi-scale and multi-layer visualization of sequence-based intermediate representations
Escolano Peinado, Carlos; Ruiz Costa-Jussà, Marta; Lacroux, Elora; Vázquez Alcocer, Pere Pau (Association for Computational Linguistics, 2019)
Text en actes de congrés
Accés restringit per política de l'editorialThe main alternatives nowadays to dealwith sequences are Recurrent Neural Net-works (RNN), Convolutional Neural Networks(CNN) architectures and the Transformer. Inthis context, RNN’s, CNN’s and Transformerhave most commonly ... -
N-gram-based Machine Translation
Mariño Acebal, José Bernardo; Banchs Martínez, Rafael Enrique; Crego Clemente, Josep Maria; Gispert Brosa, Adrian de; Lambert, Patrik; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (2006-12)
Article
Accés obertThis article describes in detail an n-gram approach to statistical machine translation. This approach consists of a log-linear combination of a translation model based on n-grams of bilingual units, which are referred to ... -
N-II: traductor automático estadístico basado en Ngramas
Ruiz Costa-Jussà, Marta; Farrus, Mireia; Poch, Marc; Hernández Huerta, Adolfo; Mariño, José B. (2008)
Text en actes de congrés
Accés obertEsta comunicación describe el desarrollo del traductor estadístico N-II entre catalán y castellano. Para mejorar la calidad del sistema, se llevó a cabo un riguroso análisis lingüístico. Este ha permitido plantear ... -
Neural machine translation for Kashmiri to Eglish and Hindi using pre-trained embeddings
Sheshadri, Shailashree K.; Gupta, Deepa; Ruiz Costa-Jussà, Marta (Institute of Electrical and Electronics Engineers (IEEE), 2022)
Text en actes de congrés
Accés restringit per política de l'editorialNeural Machine Translation (NMT) is one of the advanced approaches of Machine Translation (MT) that has recently gained popularity. A significant amount of parallel corpus is required to achieve a sound translation system, ... -
Neural machine translation using bitmap fonts
Aldón Mínguez, David; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2016)
Comunicació de congrés
Accés obertRecently, 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. However, one of the ... -
Neural machine translation with the transformer and multi-source romance languages for the biomedical WMT 2018 task
Tubay, Brian; Ruiz Costa-Jussà, Marta (2018)
Comunicació de congrés
Accés restringit per política de l'editorial -
On the locality of attention in direct speech translation
Alastruey Lasheras, Belén; Ferrando Monsonís, Javier; Gallego Olsina, Gerard Ion; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2022)
Comunicació de congrés
Accés obertTransformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long ... -
On-line and off-line Chinese-Portuguese translation service for mobile applications
Centelles, Jordi; Ruiz Costa-Jussà, Marta; Banchs Martínez, Rafael Enrique; Gelbukh, Alexander (2014-07-01)
Article
Accés obertWe describe a Chinese-Portuguese translation service, which is integrated in an Android application. The application is also enhanced with technologies such as Automatic Speech Recognition, Optical Character Recognition, ... -
Ongoing study for enhancing chinese-spanish translation with morphology strategies
Ruiz Costa-Jussà, Marta (2015)
Text en actes de congrés
Accés obertChinese and Spanish have different morphology structures, which poses a big challenge for translating between this pair of languages. In this paper, we analyze several strategies to better generalize from the Chinese ... -
Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
Mariño Acebal, José Bernardo; Farrús Cabeceran, Mireia; Ruiz Costa-Jussà, Marta; Poch, Marc; Hernández Huerta, Adolfo; Herníquez, Carlos; Rodríguez Fonollosa, José Adrián (2011-02-20)
Article
Accés obertThis work aims to improve anN-gram-based statistical machine translation system between the Catalan and Spanish languages, trained with an aligned Spanish– Catalan parallel corpus consisting of 1.7 million sentences taken ... -
Plagiarism detection using information retrieval and similarity measures based on image processing techniques
Ruiz Costa-Jussà, Marta; Banchs, Rafael E.; Grivolla, Jens; Codina, Joan (2010)
Text en actes de congrés
Accés obertThis paper describes the Barcelona Media Innovation Center participation in the 2nd International Competition on Plagiarism Detection. Particularly, our system focused on the external plagiarism detection task, which assumes ... -
Refinement of unsupervised cross-lingual word embeddings
Biesialska, Magdalena Marta; Ruiz Costa-Jussà, Marta (Ios Press, 2020)
Comunicació de congrés
Accés obertCross-lingual word embeddings aim to bridge the gap between high-resource and low-resource languages by allowing to learn multilingual word representations even without using any direct bilingual signal. The lion's share ...