Phrase Grounding by Soft-Label Chain Conditional Random Field

Jiacheng Liu, Julia Hockenmaier


Abstract
The phrase grounding task aims to ground each entity mention in a given caption of an image to a corresponding region in that image. Although there are clear dependencies between how different mentions of the same caption should be grounded, previous structured prediction methods that aim to capture such dependencies need to resort to approximate inference or non-differentiable losses. In this paper, we formulate phrase grounding as a sequence labeling task where we treat candidate regions as potential labels, and use neural chain Conditional Random Fields (CRFs) to model dependencies among regions for adjacent mentions. In contrast to standard sequence labeling tasks, the phrase grounding task is defined such that there may be multiple correct candidate regions. To address this multiplicity of gold labels, we define so-called Soft-Label Chain CRFs, and present an algorithm that enables convenient end-to-end training. Our method establishes a new state-of-the-art on phrase grounding on the Flickr30k Entities dataset. Analysis shows that our model benefits both from the entity dependencies captured by the CRF and from the soft-label training regime. Our code is available at github.com/liujch1998/SoftLabelCCRF
Anthology ID:
D19-1515
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5112–5122
Language:
URL:
https://aclanthology.org/D19-1515
DOI:
10.18653/v1/D19-1515
Bibkey:
Cite (ACL):
Jiacheng Liu and Julia Hockenmaier. 2019. Phrase Grounding by Soft-Label Chain Conditional Random Field. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5112–5122, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Phrase Grounding by Soft-Label Chain Conditional Random Field (Liu & Hockenmaier, EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1515.pdf
Attachment:
 D19-1515.Attachment.zip
Code
 liujch1998/SoftLabelCCRF
Data
Flickr30K Entities