Multimodal Machine Translation with Embedding Prediction

@article{Hirasawa2019MultimodalMT,
  title={Multimodal Machine Translation with Embedding Prediction},
  author={Tosho Hirasawa and Hayahide Yamagishi and Yukio Matsumura and Mamoru Komachi},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.00639}
}
Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from a shortage of available training data, resulting in poor performance for translating rare words. In NMT, pretrained word embeddings have been shown to improve NMT of low-resource domains, and a search-based approach is proposed to address the rare word… Expand
6 Citations

References

SHOWING 1-10 OF 21 REFERENCES
When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?
  • 151
  • Highly Influential
  • PDF
The MeMAD Submission to the WMT18 Multimodal Translation Task
  • 32
  • PDF
Neural Machine Translation of Rare Words with Subword Units
  • 3,354
  • PDF
Doubly-Attentive Decoder for Multi-modal Neural Machine Translation
  • 93
  • PDF
Neural Machine Translation by Jointly Learning to Align and Translate
  • 14,961
  • Highly Influential
  • PDF
Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs
  • 39
  • PDF
CUNI System for the WMT18 Multimodal Translation Task
  • 28
  • PDF
Imagination Improves Multimodal Translation
  • 77
  • Highly Influential
  • PDF
...
1
2
3
...