Ara es mostren els items 21-40 de 135

    • BERT masked language modeling for co-reference resolution 

      Alfaro, Felipe; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2019)
      Text en actes de congrés
      Accés obert
      This paper explains the TALP-UPC participation for the Gendered Pronoun Resolution shared-task of the 1st ACL Workshop on Gender Bias for Natural Language Processing. We have implemented two models for mask language modeling ...
    • Bridging deep and kernel methods 

      Belanche Muñoz, Luis Antonio; Ruiz Costa-Jussà, Marta (2017)
      Text en actes de congrés
      Accés obert
      There has been some exciting major progress in recent years in data analysis methods, including a variety of deep learning architectures, as well as further advances in kernel-based learning methods, which have demonstrated ...
    • BUCEADOR, a multi-language search engine for digital libraries 

      Adell Mercado, Jordi; Bonafonte Cávez, Antonio; Cardenal, Antonio; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián; Moreno Bilbao, M. Asunción; Navas, Eva; Rodríguez Banga, Eduardo (2012)
      Comunicació de congrés
      Accés obert
      This paper presents a web-based multimedia search engine built within the Buceador (www.buceador.org) research project. A proof-of-concept tool has been implemented which is able to retrieve information from a digital ...
    • Byte-based neural machine translation 

      Ruiz Costa-Jussà, Marta; Escolano Peinado, Carlos; Rodríguez Fonollosa, José Adrián (Association for Computational Linguistics, 2017)
      Text en actes de congrés
      Accés obert
      This paper presents experiments compar- ing character-based and byte-based neural machine translation systems. The main motivation of the byte-based neural ma- chine translation system is to build multi- lingual neural ...
    • Character-based neural machine translation 

      Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2016)
      Comunicació de congrés
      Accés obert
      Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, ...
    • Character-level intra attention networks for natural language inference 

      Yang, Han; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2017)
      Comunicació de congrés
      Accés obert
      Natural language inference (NLI) is a central problem in language understand- ing. End-to-end artificial neural networks have reached state-of-the-art performance in NLI field recently. In this paper, we propose Character- ...
    • Chatbol, a chatbot for the Spanish “La Liga” 

      Segura, Carlos; Palau, Alex; Luque, Jordi; Ruiz Costa-Jussà, Marta; Banchs, Rafael E. (Springer, 2019-09-25)
      Article
      Accés obert
      This work describes the development of a social chatbot for the football domain. The chatbot, named chatbol, aims at answering a wide variety of questions related to the Spanish football league “La Liga”. Chatbol is deployed ...
    • Chinese-Catalan: A neural machine translation approach based on pivoting and attention mechanisms 

      Ruiz Costa-Jussà, Marta; Casas Manzanares, Noé; Escolano Peinado, Carlos; Rodríguez Fonollosa, José Adrián (2019-01-01)
      Article
      Accés obert
      This article innovatively addresses machine translation from Chinese to Catalan using neural pivot strategies trained without any direct parallel data. The Catalan language is very similar to Spanish from a linguistic point ...
    • 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
      Accés obert
      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 phrase and neural-based machine translation: what worked and did not 

      Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2017)
      Article
      Accés restringit per política de l'editorial
      Phrase-based machine translation assumes that all words are at the same distance and translates them using feature functions that approximate the probability at different levels. On the other hand, neural machine translation ...
    • 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)
      Comunicació de congrés
      Accés obert
      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 ...
    • Communicating China and Latin America 

      Ruiz Costa-Jussà, Marta (2013-08-07)
      Report de recerca
      Accés restringit per política de l'editorial
    • Conclusions 

      Ruiz Costa-Jussà, Marta (2014-07-24)
      Audiovisual
      Accés obert
      Setmana 5, conclusions del MOOC "Approaches to machine translation: rule-based, statistical and hybrid".
    • Continual lifelong learning in natural language processing: a survey 

      Biesialska, Magdalena Marta; Biesialska, Katarzyna; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2020)
      Comunicació de congrés
      Accés obert
      Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting ...
    • Converses al voltant de la intel·ligència artificial en clau catalana 

      Ruiz Costa-Jussà, Marta; Melero Nogues, Maite (2020-12)
      Article
      Accés obert
      La intel·ligència artificial mou milions d’euros i ocupa una part important de les agendes polítiques i estratègiques dels governs. En aquest article reflexionem sobre aquest concepte difús i ho fem a través de tres ...
    • Coverage for character based neural machine translation 

      Kazimi, Bashir; Ruiz Costa-Jussà, Marta (2017-09-22)
      Article
      Accés obert
      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 ...
    • Dades, màquina i ètica 

      Ruiz Costa-Jussà, Marta (2019-02-01)
      Article
      Accés obert
    • DeepVoice: tecnologías de aprendizaje profundo aplicadas al procesado de voz y audio 

      Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2017-09-01)
      Article
      Accés obert
      This project proposes the development of new deep learning methods for speech and audio processing, exploring new applications and continuing the initial work of the research team and the international community. Research ...
    • DeepVoice: tecnologías de aprendizaje profundo aplicadas al procesado de voz y audio 

      Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2017-09-22)
      Article
      Accés obert
      Este proyecto propone el desarrollo de nuevas arquitecturas para el procesado de la voz y el audio mediante métodos de aprendizaje profundo, explorando también nuevas aplicaciones y dando continuidad al trabajo inicial del ...
    • 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
      Accés obert
      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. ...