We introduce a novel, simple convolution neural network (CNN) architecture -- multi-group norm constraint CNN (MGNC-CNN) -- that capitalizes on multiple sets of word embeddings for sentence classification. MGNC-CNN extracts features from input embedding sets independently and then joins these at the penultimate layer in the network to form a final feature vector. We then adopt a group regularization strategy that differentially penalizes weights associated with the subcomponents generated from the respective embedding sets. This model is much simpler than comparable alternative architectures and requires substantially less training time. Furthermore, it is flexible in that it does not require input word embeddings to be of the same dimensionality. We show that MGNC-CNN consistently outperforms baseline models.

PDF

In Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-16), pp. 1522--1527, San Diego, California 2016.

@inproceedings{zhang:naacl16, title={MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification}, author={Ye Zhang and Stephen Roller and Byron Wallace.}, booktitle={Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-16)}, address={San Diego, California}, pages={1522--1527}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127593", year={2016} }