Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
A Simple Fully Connected Network for Composing Word Embeddings from Characters
Michael Traynor, Thomas Trappenberg
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:This work introduces a simple network for producing character aware word embeddings. Position agnostic and position aware character embeddings are combined to produce an embedding vector for each word. The learned word representations are shown to be very sparse and facilitate improved results on language modeling tasks, despite using markedly fewer parameters, and without the need to apply dropout. A final experiment suggests that weight sharing contributes to sparsity, increases performance, and prevents overfitting.
TL;DR:A fully connected architecture is used to produce word embeddings from character representations, outperforms traditional embeddings and provides insight into sparsity and dropout.
Keywords:natural language processing, word embeddings, language models, neural network, deep learning, sparsity, dropout
Enter your feedback below and we'll get back to you as soon as possible.