The Role of Syntactic Planning in Compositional Image Captioning

01/28/2021 ∙ by Emanuele Bugliarello, et al. ∙ 14

Image captioning has focused on generalizing to images drawn from the same distribution as the training set, and not to the more challenging problem of generalizing to different distributions of images. Recently, Nikolaus et al. (2019) introduced a dataset to assess compositional generalization in image captioning, where models are evaluated on their ability to describe images with unseen adjective-noun and noun-verb compositions. In this work, we investigate different methods to improve compositional generalization by planning the syntactic structure of a caption. Our experiments show that jointly modeling tokens and syntactic tags enhances generalization in both RNN- and Transformer-based models, while also improving performance on standard metrics.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

page 8

page 13

page 15

Code Repositories

syncap

Code and data for our paper "The Role of Syntactic Planning in Compositional Image Captioning", EACL 2021.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.