Learning Visually Grounded Sentence Representations

Douwe Kiela, Alexis Conneau, Allan Jabri, Maximilian Nickel
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
We investigate grounded sentence representations, where we train a sentence encoder to predict the image features of a given captioni.e., we try to "imagine" how a sentence would be depicted visually-and use the resultant features as sentence representations. We examine the quality of the learned representations on a variety of standard sentence representation quality benchmarks, showing improved performance for grounded models over non-grounded ones. In addition, we thoroughly analyze the
more » ... t to which grounding contributes to improved performance, and show that the system also learns improved word embeddings.
doi:10.18653/v1/n18-1038 dblp:conf/naacl/KielaCJN18 fatcat:7sda73my3jguhgemoxmje6fhca