Image-Mediated Learning for Zero-Shot Cross-Lingual Document Retrieval

@inproceedings{Funaki2015ImageMediatedLF,
  title={Image-Mediated Learning for Zero-Shot Cross-Lingual Document Retrieval},
  author={Ruka Funaki and Hideki Nakayama},
  booktitle={EMNLP},
  year={2015}
}
We propose an image-mediated learning approach for cross-lingual document retrieval where no or only a few parallel corpora are available. Using the images in image-text documents of each language as the hub, we derive a common semantic subspace bridging two languages by means of generalized canonical correlation analysis. For the purpose of evaluation, we create and release a new document dataset consisting of three types of data (English text, Japanese text, and images). Our approach… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 21 extracted citations

Zero-Shot Cross-Lingual Neural Headline Generation

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2018
View 1 Excerpt

Explorer Image Pivoting for Learning Multilingual Multimodal Representations

Spandana Gella Rico Sennrich Frank Keller Mirella Lapata
2017
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 23 references

Relations between Two Sets of Variants

Harold Hotelling.
Biometrika, 28:321–377. • 1936
View 12 Excerpts
Highly Influenced

Caffe: Convolutional Architecture for Fast Feature Embedding

ACM Multimedia • 2014
View 5 Excerpts
Highly Influenced

From captions to visual concepts and back

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 1 Excerpt

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 3 Excerpts

ImageNet Large Scale Visual Recognition Challenge

International Journal of Computer Vision • 2015
View 3 Excerpts

Going deeper with convolutions . CoRR abs / 1409 . 4842

Mitesh M Khapra
2014

Similar Papers

Loading similar papers…