Hypernymy, textual entailment, and image captioning can be seen as special
cases of a single visual-semantic hierarchy over words, sentences, and images.
In this paper we advocate for explicitly modeling the partial order structure
of this hierarchy. Towards this goal, we introduce a general method for
learning ordered representations, and show how it can be applied to a variety
of tasks involving images and language. We show that the resulting
representations improve performance over current approaches for hypernym
prediction and image-caption retrieval.
Description
[1511.06361] Order-Embeddings of Images and Language
%0 Generic
%1 vendrov2015orderembeddings
%A Vendrov, Ivan
%A Kiros, Ryan
%A Fidler, Sanja
%A Urtasun, Raquel
%D 2015
%K embedding tree
%T Order-Embeddings of Images and Language
%U http://arxiv.org/abs/1511.06361
%X Hypernymy, textual entailment, and image captioning can be seen as special
cases of a single visual-semantic hierarchy over words, sentences, and images.
In this paper we advocate for explicitly modeling the partial order structure
of this hierarchy. Towards this goal, we introduce a general method for
learning ordered representations, and show how it can be applied to a variety
of tasks involving images and language. We show that the resulting
representations improve performance over current approaches for hypernym
prediction and image-caption retrieval.
@misc{vendrov2015orderembeddings,
abstract = {Hypernymy, textual entailment, and image captioning can be seen as special
cases of a single visual-semantic hierarchy over words, sentences, and images.
In this paper we advocate for explicitly modeling the partial order structure
of this hierarchy. Towards this goal, we introduce a general method for
learning ordered representations, and show how it can be applied to a variety
of tasks involving images and language. We show that the resulting
representations improve performance over current approaches for hypernym
prediction and image-caption retrieval.},
added-at = {2021-07-05T14:41:30.000+0200},
author = {Vendrov, Ivan and Kiros, Ryan and Fidler, Sanja and Urtasun, Raquel},
biburl = {https://www.bibsonomy.org/bibtex/2b1f5eec618d4efbff6e50a81f12155e2/parismic},
description = {[1511.06361] Order-Embeddings of Images and Language},
interhash = {7e04d9f68242eee5e3eab33b1d8f80cf},
intrahash = {b1f5eec618d4efbff6e50a81f12155e2},
keywords = {embedding tree},
note = {cite arxiv:1511.06361Comment: ICLR camera-ready version},
timestamp = {2021-07-05T14:41:30.000+0200},
title = {Order-Embeddings of Images and Language},
url = {http://arxiv.org/abs/1511.06361},
year = 2015
}