Now showing items 21-40 of 123

    • Chinese–Spanish neural machine translation enhanced with character and word bitmap fonts 

      Ruiz Costa-Jussà, Marta; Aldón Mínguez, David; Rodríguez Fonollosa, José Adrián (2017-04-06)
      Article
      Open Access
      Recently, machine translation systems based on neural networks have reached state-of-the-art results for some pairs of languages (e.g., German–English). In this paper, we are investigating the performance of neural machine ...
    • Combining subword representations into word-level representations in the transformer architecture 

      Casas Manzanares, Noé; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (Association for Computational Linguistics, 2020)
      Conference lecture
      Open Access
      In Neural Machine Translation, using word-level tokens leads to degradation in translation quality. The dominant approaches use subword-level tokens, but this increases the length of the sequences and makes it difficult ...
    • Context-aware machine translation for software localization 

      Muntés Mulero, Víctor; Paladini Adell, Patricia; España Bonet, Cristina; Màrquez Villodre, Lluís (2012)
      Conference lecture
      Open Access
      Software localization requires translating short text strings appearing in user interfaces (UI) into several languages. These strings are usually unrelated to the other strings in the UI. Due to the lack of semantic ...
    • Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation 

      Dras, Mark; Khalilov, Maxim; Rodríguez Fonollosa, José Adrián (2009-06)
      Conference lecture
      Open Access
      In this paper, we start with the existing idea of taking reordering rules automatically derived from syntactic representations, and applying them in a preprocessing step before translation to make the source sentence ...
    • Coverage for character based neural machine translation 

      Kazimi, Bashir; Ruiz Costa-Jussà, Marta (2017-09-22)
      Article
      Open Access
      In recent years, Neural Machine Translation (NMT) has achieved state-of-the-art performance in translating from a language; source language, to another; target language. However, many of the proposed methods use word ...
    • Cross-modal neural sign language translation 

      Cardoso Duarte, Amanda (Association for Computing Machinery (ACM), 2019)
      Conference report
      Open Access
      Sign Language is the primary means of communication for the majority of the Deaf and hard-of-hearing communities. Current computational approaches in this general research area have focused specifically on sign language ...
    • Decision, Integration and Deployment of a Translation Management Software 

      Roselló Rosiñol, Aleix (Universitat Politècnica de Catalunya, 2020-06)
      Bachelor thesis
      Open Access
      Covenantee:   Andjoy
      En un context de globalització i internacionalització, les diferents aplicacions de software poden ser utilitzades a tot el món i en regions diferents. Per aquest motiu, les empreses estan obligades a traduir el contingut ...
    • Deep evaluation of hybrid architectures: simple metrics correlated with human judgments 

      Labaka, Gorka; Díaz de Ilarraza Sánchez, Arantza; Sarasola Gabiola, Kepa; España Bonet, Cristina; Màrquez Villodre, Lluís (2011)
      Conference lecture
      Open Access
      The process of developing hybrid MT systems is guided by the evaluation method used to compare different combinations of basic subsystems. This work presents a deep evaluation experiment of a hybrid architecture ...
    • Description of the Chinese-to-Spanish rule-based machine translation system developed with a hybrid combination of human annotation and statistical techniques 

      Ruiz Costa-Jussà, Marta; Centelles, Jordi (2015-11-01)
      Article
      Open Access
      Two of the most popular Machine Translation (MT) paradigms are rule based (RBMT) and corpus based, which include the statistical systems (SMT). When scarce parallel corpus is available, RBMT becomes particularly attractive. ...
    • Document-level machine translation as a re-translation process 

      Martínez Garcia, Eva; España Bonet, Cristina; Màrquez Villodre, Lluís (2014-09-22)
      Article
      Open Access
      Most of the current Machine Translation systems are designed to translate a document sentence by sentence ignoring discourse information and producing incoherencies in the final translations. In this paper we present some ...
    • Document-level machine translation with word vector models 

      Martínez Garcia, Eva; España Bonet, Cristina; Márquez Villodre, Luís (2015)
      Conference report
      Open Access
      In this paper we apply distributional semantic information to document-level machine translation. We train monolingual and bilingual word vector models on large corpora and we evaluate them first in a cross-lingual lexical ...
    • Domain adaptation strategies in statistical machine translation: a brief overview 

      Ruiz Costa-Jussà, Marta (2015-11-01)
      Article
      Open Access
      Statistical machine translation (SMT) is gaining interest given that it can easily be adapted to any pair of languages. One of the main challenges in SMT is domain adaptation because the performance in translation drops ...
    • Empirical machine translation and its evaluation 

      Giménez Linares, Jesús Ángel (Universitat Politècnica de Catalunya, 2008-07-02)
      Doctoral thesis
      Open Access
      Aquesta tesi estudia l'aplicació de les tecnologies del Processament del Llenguatge Natural disponibles actualment al problema de la Traducció Automàtica basada en Mètodes Empírics i la seva Avaluació.<br/><br/>D'una banda, ...
    • End-to-end speech translation system with attention-based mechanisms 

      Cros Vila, Laura (Universitat Politècnica de Catalunya, 2018-06)
      Bachelor thesis
      Open Access
      Speech Recognition and Text-to-Text Translation systems have been improving significantly in recent decades thanks to the improvement of both hardware and software means. However, Speech Translation is usually done as a ...
    • End-to-end speech translation with the transformer 

      Cross Vila, Laura; Escolano Peinado, Carlos; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (Antonio Bonafonte, Jordi Luque and Francesc Alías Pujol, 2018)
      Conference lecture
      Restricted access - publisher's policy
      Speech Translation has been traditionally addressed with the concatenation of two tasks: Speech Recognition and Machine Translation. This approach has the main drawback that errors are concatenated. Recently, neural ...
    • English-catalan neural machine translation in the biomedical domain through the cascade approach 

      Ruiz Costa-Jussà, Marta; Casas, Noe; Melero, Maite (2018)
      Conference lecture
      Restricted access - publisher's policy
      This paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair. This task can be considered a low-resourced task from the point of ...
    • English-to-Hindi system description for WMT 2014: deep source-context features for Moses 

      Ruiz Costa-Jussà, Marta; Gupta, Parth; Banchs, Rafael E.; Rosso, P. (Association for Computational Linguistics, 2014)
      Conference lecture
      Open Access
      This paper describes the IPN-UPV participation on the English-to-Hindi translation task from WMT 2014 International Evaluation Campaign. The system presented is based on Moses and enhanced with deep learning by meansof ...
    • Enhancing scarce-resource language translation through pivot combinations 

      Ruiz Costa-Jussà, Marta; Henríquez, Carlos; Banchs, Rafael E. (2011)
      Conference report
      Open Access
      Chinese and Spanish are the most spoken languages in the world. However, there is not much research done in machine translation for this language pair. We experiment with the parallel Chinese-Spanish corpus (United Nations) ...
    • Experimental research on encoder-decoder architectures with attention for chatbots 

      Ruiz Costa-Jussà, Marta; Nuez, Álvaro; Segura, Carlos (2018-03-18)
      Article
      Restricted access - publisher's policy
      Chatbots aim at automatically offering a conversation be- tween a human and a computer. While there is a long track of re- search in rule-based and retrieval-based approaches, the generation-based approaches are promisingly ...
    • Experiments on document level machine translation 

      Martínez Garcia, Eva; España Bonet, Cristina; Márquez Villodre, Luís (2014-03-03)
      External research report
      Open Access
      Most of the current SMT systems work at sentence level. They translate a text assuming that sentences are independent, but, when one looks at a well formed document, it is clear that there exist many inter sentence relations. ...