Attention-based Multimodal Neural Machine Translation

Autor:	Chris Dyer, Po-Yao Huang, Frederick Liu, Sz-Rung Shiang, Jean Oh
Rok vydání:	2016
Předmět:	Machine translation business.industry Computer science Speech recognition computer.software_genre Translation (geometry) Multiple modalities Artificial intelligence Representation (mathematics) business computer Encoder Natural language processing Decoding methods
Zdroj:	WMT
DOI:	10.18653/v1/w16-2360
Popis:	We present a novel neural machine translation (NMT) architecture associating visual and textual features for translation tasks with multiple modalities. Transformed global and regional visual features are concatenated with text to form attendable sequences which are dissipated over parallel long short-term memory (LSTM) threads to assist the encoder generating a representation for attention-based decoding. Experiments show that the proposed NMT outperform the text-only baseline.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::e810cd7ba3fcfa6cda2cb6b55b242048 https://doi.org/10.18653/v1/w16-2360 Zobrazit plný text záznamu