• Publications
  • Influence
How2: A Large-scale Dataset for Multimodal Language Understanding
TLDR
We introduce How2, a multimodal collection of instructional videos paired with spoken utterances, English subtitles and their crowdsourced Portuguese translations, as well as English video summaries. Expand
LIUM-CVC Submissions for WMT17 Multimodal Translation Task
TLDR
This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation. Expand
Probing the Need for Visual Context in Multimodal Machine Translation
TLDR
We probe the contribution of the visual modality to state-of-the-art MMT models by conducting a systematic analysis where we partially deprive the models from source-side textual context and show that under limited textual context, models are capable of leveraging the visual input to generate better translations. Expand
Does Multimodality Help Human and Machine for Translation and Image Captioning?
TLDR
This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. Expand
NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems
TLDR
We present nmtpy, a flexible Python toolkit based on Theano for training Neural Machine Translation and other neural sequence-to-sequence architectures. Expand
Multimodal Grounding for Sequence-to-sequence Speech Recognition
TLDR
We propose novel end-to-end multimodal ASR systems and compare them to the adaptive approach by using a range of visual representations obtained from state-of-the-art convolutional neural networks. Expand
Multimodal Attention for Neural Machine Translation
TLDR
The attention mechanism is an important part of the neural machine translation (NMT) where it was reported to produce richer source representation compared to fixed-length encoding sequence-to-sequence models. Expand
LIUM-CVC Submissions for WMT18 Multimodal Translation Task
TLDR
This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. Expand
Sustainable computational science: the ReScience initiative
TLDR
ReScience is a peer-reviewed journal that targets computational research and encourages the explicit replication of already published research, promoting new and open-source implementations in order to ensure that the original research can be replicated from its description. Expand
Multimodal machine translation through visuals and speech
TLDR
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. Expand
...
1
2
3
...