Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO
Zarana Parekh, Jason Baldridge, Daniel M. Cer, Austin Waters, Yinfei Yang · 2021
By supporting multi-modal retrieval training and evaluation, image captioning datasets have spurred remarkable progress on representation learning.Unfortunately, datasets have limited cross-modal associations: images are not paired with other images, captions are only paired with other captions of the same image, there are no negative associations and there are missing positive cross-modal associations.This undermines research into how inter-modality learning impacts intra-modality tasks.We address this gap with Crisscrossed Captions (CxC), an extension of the MS-COCO dataset with human semantic similarity judgments for 267,095 intra-and intermodality pairs.We report baseline results on CxC for strong existing unimodal and multimodal models.We also evaluate a multitask dual encoder trained on both image-caption and caption-caption pairs that crucially demonstrates CxC's value for measuring the influence of intra-and inter-modality learning.