Vision and Feature Norms: Improving automatic feature norm learning through cross-modal maps Vision and Feature Norms: Improving automatic feature norm learning through cross-modal maps
Paper summary The task is to predict feature norms – object properties, for example is_yellow and is_edible for the word banana. They experiment with adding in image recognition features, in addition to using distributional word vectors. An input word is used to retrieve 10 images from Google, these are passed through an ImageNet classifier to get feature vectors, and then averaged to get a vector representation for that word. A supervised model (partial least-squares regression) is then trained to predict vectors of feature norms based on the input vectors (image-based, distributional, or a combination). Including the image information helps quite a bit, especially for detecting properties like colour and shape. https://i.imgur.com/4TYKhvm.png Examples of predicted feature norms using the visual features.
aclweb.org
sci-hub
scholar.google.com
Vision and Feature Norms: Improving automatic feature norm learning through cross-modal maps
Bulat, Luana and Kiela, Douwe and Clark, Stephen
The Association for Computational Linguistics HLT-NAACL - 2016 via Local Bibsonomy
Keywords: dblp


Summary by Marek Rei 8 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and