Exploration on Grounded Word Embedding: Matching Words and Images with Image-Enhanced Skip-Gram Model

Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors. The state-of-the-art methods of learning word embeddings (word2vec and GloVe) only use the word co-occurrence information. The learned embeddings are real number vectors, which are obscure to human....

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-09
Main Author: Luo, Ruixuan
Format: Article
Language:English
Subjects:
Embedding
Image enhancement
State vectors
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors. The state-of-the-art methods of learning word embeddings (word2vec and GloVe) only use the word co-occurrence information. The learned embeddings are real number vectors, which are obscure to human. In this paper, we propose an Image-Enhanced Skip-Gram Model to learn grounded word embeddings by representing the word vectors in the same hyper-plane with image vectors. Experiments show that the image vectors and word embeddings learned by our model are highly correlated, which indicates that our model is able to provide a vivid image-based explanation to the word embeddings.
ISSN:2331-8422