Projects per year
In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model learns a common representation for images and their descriptions in two different languages (which need not be parallel) by considering the image as a pivot between two languages. We introduce a new pairwise ranking loss function which can handle both symmetric and asymmetric similarity between the two modalities. We evaluate our models on image-description ranking for German and English, and on semantic textual similarity of image descriptions in English. In both cases we achieve state-of-the-art performance.
|Title of host publication||Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing|
|Place of Publication||Copenhagen, Denmark|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||7|
|Publication status||Published - 11 Sep 2017|
|Event||EMNLP 2017: Conference on Empirical Methods in Natural Language Processing - Copenhagen, Denmark|
Duration: 7 Sep 2017 → 11 Sep 2017
|Conference||EMNLP 2017: Conference on Empirical Methods in Natural Language Processing|
|Abbreviated title||EMNLP 2017|
|Period||7/09/17 → 11/09/17|
FingerprintDive into the research topics of 'Image Pivoting for Learning Multilingual Multimodal Representations'. Together they form a unique fingerprint.
- 1 Finished
TransModal: Translating from Multiple Modalities into Text
1/09/16 → 31/08/22