@InProceedings{han-EtAl:2018:Long,
  author    = {Han, Jialong  and  Song, Yan  and  Zhao, Wayne Xin  and  Shi, Shuming  and  Zhang, Haisong},
  title     = {hyperdoc2vec: Distributed Representations of Hypertext Documents},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {2384--2394},
  abstract  = {Hypertext documents, such as web pages and academic papers, are of great importance in delivering information in our daily life. Although being effective on plain documents, conventional text embedding methods suffer from information loss if directly adapted to hyper-documents. In this paper, we propose a general embedding approach for hyper-documents, namely, hyperdoc2vec, along with four criteria characterizing necessary information that hyper-document embedding models should preserve. Systematic comparisons are conducted between hyperdoc2vec and several competitors on two tasks, i.e., paper classification and citation recommendation, in the academic paper domain. Analyses and experiments both validate the superiority of hyperdoc2vec to other models w.r.t. the four criteria.},
  url       = {http://www.aclweb.org/anthology/P18-1222}
}