@inproceedings{yang-etal-2017-neural,
    title = "Neural Reranking for Named Entity Recognition",
    author = "Yang, Jie  and
      Zhang, Yue  and
      Dong, Fei",
    booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
    month = sep,
    year = "2017",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd.",
    url = "https://doi.org/10.26615/978-954-452-049-6_101",
    doi = "10.26615/978-954-452-049-6_101",
    pages = "784--792",
    abstract = "We propose a neural reranking system for named entity recognition (NER),leverages recurrent neural network models to learn sentence-level patterns thatinvolve named entity mentions. In particular, given an output sentence producedby a baseline NER model, we replace all entity mentions, such as \textit{BarackObama}, into their entity types, such as \textit{PER}. The resulting sentencepatterns contain direct output information, yet is less sparse without specificnamed entities. For example, {``}PER was born in LOC{''} can be such a pattern.LSTM and CNN structures are utilised for learning deep representations of suchsentences for reranking. Results show that our system can significantly improvethe NER accuracies over two different baselines, giving the best reportedresults on a standard benchmark.",
}