WMT 2016 Multimodal translation system description based on bidirectional recurrent neural networks with double-embeddings
Tipus de documentText en actes de congrés
Condicions d'accésAccés obert
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.
CitacióRodríguez Guasch, S., Ruiz, M. WMT 2016 Multimodal translation system description based on bidirectional recurrent neural networks with double-embeddings. A: Conference on Machine Translation. "ACL 2016 : the 54th Annual Meeting of the Association for Computational Linguistics : proceedings of the First Conference on Machine Translation (WMT)". 0, p. 655-659.
Versió de l'editorhttp://www.statmt.org/wmt16/pdf/W16-2362.pdf