2026-04-13T13:42:21Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/1028392025-07-17T09:46:30Zcom_2072_1033col_2072_452950

00925njm 22002777a 4500 dc Rodríguez Guasch, Sergio author Ruiz Costa-Jussà, Marta author 2016 Bidirectional Recurrent Neural Networks (BiRNNs) have shown outstanding results on sequence-to-sequence learning tasks. This architecture becomes specially interesting for multimodal machine translation task, since BiRNNs can deal with images and text. On most translation systems the same word embedding is fed to both BiRNN units. In this paper, we present several experiments to enhance a baseline sequence-to-sequence system (Elliott et al., 2015), for example, by using double embeddings. These embeddings are trained on the forward and backward direction of the input sequence. Our system is trained, validated and tested on the Multi30K dataset (Elliott et al., 2016) in the context of theWMT 2016Multimodal Translation Task. The obtained results show that thedouble-embedding approach performs significantly better than the traditional single-embedding one. Postprint (published version) Àrees temàtiques de la UPC::Informàtica Machine translation Neural networks Machine translation Traducció automàtica WMT 2016 Multimodal translation system description based on bidirectional recurrent neural networks with double-embeddings