@inproceedings{mohammadshahi-etal-2019-aligning,
    title = "Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task",
    author = "Mohammadshahi, Alireza  and
      Lebret, R{\'e}mi  and
      Aberer, Karl",
    editor = "Mogadala, Aditya  and
      Klakow, Dietrich  and
      Pezzelle, Sandro  and
      Moens, Marie-Francine",
    booktitle = "Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D19-6402",
    doi = "10.18653/v1/D19-6402",
    pages = "11--17",
    abstract = "In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint embedding space while adapting the alignment of word embeddings between existing languages in our model. We show that our approach enables better generalization, achieving state-of-the-art performance in text-to-image and image-to-text retrieval task, and caption-caption similarity task. Two multimodal multilingual datasets are used for evaluation: Multi30k with German and English captions and Microsoft-COCO with English and Japanese captions.",
}