@inproceedings{li-etal-2019-strength,
    title = "The Strength of the Weakest Supervision: Topic Classification Using Class Labels",
    author = "Li, Jiatong  and
      Zheng, Kai  and
      Xu, Hua  and
      Mei, Qiaozhu  and
      Wang, Yue",
    editor = "Kar, Sudipta  and
      Nadeem, Farah  and
      Burdick, Laura  and
      Durrett, Greg  and
      Han, Na-Rae",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Student Research Workshop",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/N19-3004/",
    doi = "10.18653/v1/N19-3004",
    pages = "22--28",
    abstract = "When developing topic classifiers for real-world applications, we begin by defining a set of meaningful topic labels. Ideally, an intelligent classifier can understand these labels right away and start classifying documents. Indeed, a human can confidently tell if an article is about science, politics, sports, or none of the above, after knowing just the class labels. We study the problem of training an initial topic classifier using only class labels. We investigate existing techniques for solving this problem and propose a simple but effective approach. Experiments on a variety of topic classification data sets show that learning from class labels can save significant initial labeling effort, essentially providing a ``free'' warm start to the topic classifier."
}