Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Distributional Models and Deep Learning Embeddings: Combining the Best of Both Worlds
Irina Sergienya, Hinrich Schütze
Dec 20, 2013 (modified: Dec 20, 2013)ICLR 2014 workshop submissionreaders: everyone
Decision:submitted, no decision
Abstract:There are two main approaches to the distributed representation of words: low-dimensional deep learning embeddings and high-dimensional distributional models, in which each dimension corresponds to a context word. In this paper, we combine these two approaches by learning embeddings based on distributional-model vectors - as opposed to one-hot vectors as is standardly done in deep learning. We show that the combined approach has better performance on a word relatedness judgment task.
Enter your feedback below and we'll get back to you as soon as possible.