@inproceedings{pivovarova-yangarber-2018-comparison,
    title = "Comparison of Representations of Named Entities for Document Classification",
    author = "Pivovarova, Lidia  and
      Yangarber, Roman",
    editor = "Augenstein, Isabelle  and
      Cao, Kris  and
      He, He  and
      Hill, Felix  and
      Gella, Spandana  and
      Kiros, Jamie  and
      Mei, Hongyuan  and
      Misra, Dipendra",
    booktitle = "Proceedings of the Third Workshop on Representation Learning for {NLP}",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-3008/",
    doi = "10.18653/v1/W18-3008",
    pages = "64--68",
    abstract = "We explore representations for multi-word names in text classification tasks, on Reuters (RCV1) topic and sector classification. We find that: the best way to treat names is to split them into tokens and use each token as a separate feature; NEs have more impact on sector classification than topic classification; replacing NEs with entity types is not an effective strategy; representing tokens by different embeddings for proper names vs. common nouns does not improve results. We highlight the improvements over state-of-the-art results that our CNN models yield."
}