@inproceedings{eric-2017-document,
    title = "Document retrieval and question answering in medical documents. A large-scale corpus challenge.",
    author = "Eric, Curea",
    editor = "Boytcheva, Svetla  and
      Cohen, Kevin Bretonnel  and
      Savova, Guergana  and
      Angelova, Galia",
    booktitle = "Proceedings of the Biomedical {NLP} Workshop associated with {RANLP} 2017",
    month = sep,
    year = "2017",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd.",
    url = "https://doi.org/10.26615/978-954-452-044-1_001",
    doi = "10.26615/978-954-452-044-1_001",
    pages = "1--7",
    abstract = "Whenever employed on large datasets, information retrieval works by isolating a subset of documents from the larger dataset and then proceeding with low-level processing of the text. This is usually carried out by means of adding index-terms to each document in the collection. In this paper we deal with automatic document classification and index-term detection applied on large-scale medical corpora. In our methodology we employ a linear classifier and we test our results on the BioASQ training corpora, which is a collection of 12 million MeSH-indexed medical abstracts. We cover both term-indexing, result retrieval and result ranking based on distributed word representations.",
}