@InProceedings{meng-EtAl:2017:SemEval1,
  author    = {Meng, Fanqing  and  Lu, Wenpeng  and  Zhang, Yuteng  and  Cheng, Jinyong  and  Du, Yuehan  and  Han, Shuwang},
  title     = {QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings},
  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     = {150--153},
  abstract  = {This paper reports the details of our submissions in the task 1 of SemEval
	2017. This task aims at assessing the semantic textual similarity of two
	sentences or texts. We submit three unsupervised systems based on word
	embeddings. The differences between these runs are the various preprocessing on
	evaluation data. The best performance of these systems on the evaluation of
	Pearson correlation is 0.6887. Unsurprisingly, results of our runs demonstrate
	that data preprocessing, such as tokenization, lemmatization, extraction of
	content words and removing stop words, is helpful and plays a significant role
	in improving the performance of models.},
  url       = {http://www.aclweb.org/anthology/S17-2020}
}