I
Iacer Calixto
Researcher at New York University
Publications - 42
Citations - 1034
Iacer Calixto is an academic researcher from New York University. The author has contributed to research in topics: Machine translation & Computer science. The author has an hindex of 14, co-authored 34 publications receiving 737 citations. Previous affiliations of Iacer Calixto include University of Amsterdam & Universidade Federal de Goiás.
Papers
More filters
Journal ArticleDOI
Is Neural Machine Translation the New State of the Art
TL;DR: Comparing the quality of NMT systems with statistical MT is compared by describing three studies using automatic and human evaluation methods by reporting increases in fluency but inconsistent results for adequacy and post-editing effort.
Proceedings ArticleDOI
Incorporating Global Visual Features into Attention-based Neural Machine Translation.
Iacer Calixto,Qun Liu +1 more
TL;DR: This work introduces multi-modal, attention-based neural machine translation (NMT) models which incorporate visual features into different parts of both the encoder and the decoder, and reports new state-of-the-art results.
Proceedings ArticleDOI
Doubly-Attentive Decoder for Multi-modal Neural Machine Translation
TL;DR: The authors introduce a doubly-attentive decoder to attend to source-language words and parts of an image independently by means of two separate attention mechanisms as it generates words in the target language.
Posted Content
Doubly-Attentive Decoder for Multi-modal Neural Machine Translation
TL;DR: A Multi-modal Neural Machine Translation model in which a doubly-attentive decoder naturally incorporates spatial visual features obtained using pre-trained convolutional neural networks, bridging the gap between image description and translation.
Proceedings ArticleDOI
DCU-UvA Multimodal MT System Report
TL;DR: A doubly-attentive multimodal machine translation model that learns to attend to source language and spatial-preserving CONV5,4 visual features as separate attention mechanisms in a neural translation model is presented.