@inproceedings{meng-etal-2017-temporal,
    title = "Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an {LSTM}-based Architecture",
    author = "Meng, Yuanliang  and
      Rumshisky, Anna  and
      Romanov, Alexey",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/D17-1092/",
    doi = "10.18653/v1/D17-1092",
    pages = "887--896",
    abstract = "In this paper, we propose to use a set of simple, uniform in architecture LSTM-based models to recover different kinds of temporal relations from text. Using the shortest dependency path between entities as input, the same architecture is used to extract intra-sentence, cross-sentence, and document creation time relations. A {\textquotedblleft}double-checking{\textquotedblright} technique reverses entity pairs in classification, boosting the recall of positive cases and reducing misclassifications between opposite classes. An efficient pruning algorithm resolves conflicts globally. Evaluated on QA-TempEval (SemEval2015 Task 5), our proposed technique outperforms state-of-the-art methods by a large margin. We also conduct intrinsic evaluation and post state-of-the-art results on Timebank-Dense."
}