2016/10/07 by Marta R. Costa‐jussà, Marta R. Costa-jussà, Costa-jussà, Marta R. +2
Chemistry · Computer Science · Mathematics · #Artificial intelligence #Chemistry #Computation and Language (cs.CL) #Computer science #Deep learning #FOS: Computer and information sciences #Machine Learning (stat.ML) #Machine learning #Machine translation #Natural Language Processing Techniques #Natural language processing #Text and Document Classification Technologies #Topic Modeling #Translation (biology) #cs.CL #stat.ML
paper · pdf · doi:10.48550/arxiv.1610.02209
openalex publication_date 2016/10/07 · openalex created_date 2016/10/21 · arxiv created 2017/02/06 · arxiv updated 2017/02/07 · openalex updated_date 2026/07/28
Morphology in unbalanced languages remains a big challenge in the context of machine translation. In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem. We investigate the morphology simplification with a reasonable trade-off between expected gain and generation complexity. For the Chinese-Spanish task, optimum morphological simplification is in gender and number. For this purpose, we design a new classification architecture which, compared to other standard machine learning techniques, obtains the best results. This proposed neural-based architecture consists of several layers: an embedding, a convolutional followed by a recurrent neural network and, finally, ends with sigmoid and softmax layers. We obtain classification results over 98% accuracy in gender classification, over 93% in number classification, and an overall translation improvement of 0.7 METEOR.