Grounded Compositional Semantics for Finding and Describing Images with Sentences

Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, Andrew Y. Ng


Abstract
Previous work on Recursive Neural Networks (RNNs) shows that these models can produce compositional feature vectors for accurately representing and classifying sentences or images. However, the sentence vectors of previous models cannot accurately represent visually grounded meaning. We introduce the DT-RNN model which uses dependency trees to embed sentences into a vector space in order to retrieve images that are described by those sentences. Unlike previous RNN-based models which use constituency trees, DT-RNNs naturally focus on the action and agents in a sentence. They are better able to abstract from the details of word order and syntactic expression. DT-RNNs outperform other recursive and recurrent neural networks, kernelized CCA and a bag-of-words baseline on the tasks of finding an image that fits a sentence description and vice versa. They also give more similar representations to sentences that describe the same image.
Anthology ID:
Q14-1017
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
207–218
Language:
URL:
https://aclanthology.org/Q14-1017
DOI:
10.1162/tacl_a_00177
Bibkey:
Cite (ACL):
Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, and Andrew Y. Ng. 2014. Grounded Compositional Semantics for Finding and Describing Images with Sentences. Transactions of the Association for Computational Linguistics, 2:207–218.
Cite (Informal):
Grounded Compositional Semantics for Finding and Describing Images with Sentences (Socher et al., TACL 2014)
Copy Citation:
PDF:
https://aclanthology.org/Q14-1017.pdf
Data
ImageNet