Juan Antonio Pérez-Ortiz

Learn More
This paper describes the current status of development of an open-source shallow-transfer machine translation (MT) system for the [European] Portuguese ↔ Spanish language pair, developed using the OpenTrad Apertium MT toolbox (www.apertium.org). Apertium uses finite-state transducers for lexical processing, hidden Markov models for part-of-speech tagging,(More)
The long short-term memory (LSTM) network trained by gradient descent solves difficult problems which traditional recurrent neural networks in general cannot. We have recently observed that the decoupled extended Kalman filter training algorithm allows for even better performance, reducing significantly the number of training steps when compared to the(More)
This paper studies the use of discrete-time recurrent neural networks for predicting the next symbol in a sequence. The focus is on online prediction, a task much harder than the classical offline grammatical inference with neural networks. The results obtained show that the performance of recurrent networks working online is acceptable when sequences come(More)
When automatically translating between related languages, one of the main sources of machine translation errors is the incorrect resolution of part-of-speech (PoS) ambiguities. Hidden Markov models (HMM) are the standard statistical approach to try to properly resolve such ambiguities. The usual training algorithms collect statistics from source-language(More)
Although corpus-based approaches to machine translation (MT) are growing in interest, they are not applicable when the translation involves less-resourced language pairs for which there are no parallel corpora available; in those cases, the rule-based approach is the only applicable solution. Most rule-based MT systems make use of part-of-speech (PoS)(More)
When training hidden-Markov-model-based part-of-speech (PoS) taggers involved in machine translation systems in an unsuper-vised manner the use of target-language information has proven to give better results than the standard Baum-Welch algorithm. The target-language-driven training algorithm proceeds by translating every possible PoS tag sequence(More)
To produce fast, reasonably intelligible and easily corrected translations between related languages, it suffices to use a machine translation strategy which uses shallow parsing techniques to refine what would usually be called word-for-word machine translation. This paper describes the application of shallow parsing techniques (morphological analysis,(More)
This paper describes the machine translation (MT) system developed by the Transducens Research Group, from Universitat d'Alacant, Spain, for the WMT 2011 shared translation task. We submitted a hybrid system for the Spanish–English language pair consisting of a phrase-based statistical MT system whose phrase table was enriched with bilingual phrase pairs(More)