@InProceedings{li-EtAl:2016:COLING5,
  author    = {Li, Bofang  and  Zhao, Zhe  and  Liu, Tao  and  Wang, Puwei  and  Du, Xiaoyong},
  title     = {Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1591--1600},
  abstract  = {NBSVM is one of the most popular methods for text classification and has been
	widely used as baselines for various text representation approaches. It uses
	Naive Bayes (NB) feature to weight sparse bag-of-n-grams representation. N-gram
	captures word order in short context and NB feature assigns more weights to
	those important words. However, NBSVM suffers from sparsity problem and is
	reported to be exceeded by newly proposed distributed (dense) text
	representations learned by neural networks. In this paper, we transfer the
	n-grams and NB weighting to neural models. We train n-gram embeddings and use
	NB weighting to guide the neural models to focus on important words. In fact,
	our methods can be viewed as distributed (dense) counterparts of sparse
	bag-of-n-grams in NBSVM. We discover that n-grams and NB weighting are also
	effective in distributed representations. As a result, our models achieve new
	strong baselines on 9 text classification datasets, e.g. on IMDB dataset, we
	reach performance of 93.5\% accuracy, which exceeds previous state-of-the-art
	results obtained by deep neural models. All source codes are publicly available
	at https://github.com/zhezhaoa/neural\_BOW\_toolkit.},
  url       = {http://aclweb.org/anthology/C16-1150}
}