Learning Multilingual Word Embeddings Using Image-Text Data
This addresses the challenge of creating multilingual embeddings for low-resource languages where labeled data is scarce, though it is incremental as it builds on existing image-text approaches.
The paper tackles the problem of learning multilingual word embeddings without expensive labeled data by using weakly-supervised image-text data, achieving performance comparable to state-of-the-art methods on crosslingual semantic similarity tasks.
There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which is unavailable for low-resource languages, or have involved post-hoc unification of monolingual embeddings. In the present paper, we investigate the efficacy of multilingual embeddings learned from weakly-supervised image-text data. In particular, we propose methods for learning multilingual embeddings using image-text data, by enforcing similarity between the representations of the image and that of the text. Our experiments reveal that even without using any expensive labeled data, a bag-of-words-based embedding model trained on image-text data achieves performance comparable to the state-of-the-art on crosslingual semantic similarity tasks.