@InProceedings{sarker-gonzalez:2017:SemEval,
  author    = {Sarker, Abeed  and  Gonzalez, Graciela},
  title     = {HLP$@$UPenn at SemEval-2017 Task 4A: A simple, self-optimizing text classification system combining dense and sparse vectors},
  booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {640--643},
  abstract  = {We present a simple supervised text classification system that combines sparse
	and dense vector representations of words, and generalized representations of
	words via clusters. The sparse vectors are generated from word n-gram sequences
	(1-3). The dense vector representations of words (embeddings) are learned by
	training a neural network to predict neighboring words in a large unlabeled
	dataset. To classify a text segment, the different representations of it are
	concatenated, and the classification is performed using Support Vector Machines
	(SVM). Our system is particularly intended for use by non-experts of natural
	language processing and machine learning, and, therefore, the system does not
	require any manual tuning of parameters or weights. Given a training set, the
	system automatically generates the training vectors, optimizes the relevant
	hyper-parameters for the SVM classifier, and trains the classification model.
	We evaluated this system on the SemEval-2017 English sentiment analysis task.
	In terms of average F1-score, our system obtained 8th position out of 39
	submissions (F1-score: 0.632, average recall: 0.637, accuracy: 0.646).},
  url       = {http://www.aclweb.org/anthology/S17-2105}
}