Skeletonization: a technique for trimming the fat from a network via relevance assessment
Advances in neural information processing systems 1
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The EuTrans Spoken Language Translation System
Machine Translation
Computation of Normalized Edit Distance and Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence
Phrase-Based Statistical Machine Translation
KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Combining Pattern Classifiers: Methods and Algorithms
Combining Pattern Classifiers: Methods and Algorithms
Modeling with structures in statistical machine translation
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategies
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
An Ensemble Based Translator for Natural Languages
IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living
| Hi-index | 0.00 |
The RECONTRA translator, a simple connectionist translator between natural languages, has been able to approach several simple MT tasks. In this paper we create a variant of the RECONTRA topology which takes into account what seems to be the natural work of the human brain in the translation process: complete paragraphs or sentences are translated, not individual words. Thus, the RECONTRA translator is modified to present as output several words at the same time. Experimentally, this simple modification has shown an improvement in the translation results.