@inproceedings{li-etal-2018-end,
    title = "An End-to-End Multi-task Learning Model for Fact Checking",
    author = "Li, Sizhen  and
      Zhao, Shuai  and
      Cheng, Bo  and
      Yang, Hao",
    editor = "Thorne, James  and
      Vlachos, Andreas  and
      Cocarascu, Oana  and
      Christodoulopoulos, Christos  and
      Mittal, Arpit",
    booktitle = "Proceedings of the First Workshop on Fact Extraction and {VER}ification ({FEVER})",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-5523/",
    doi = "10.18653/v1/W18-5523",
    pages = "138--144",
    abstract = "With huge amount of information generated every day on the web, fact checking is an important and challenging task which can help people identify the authenticity of most claims as well as providing evidences selected from knowledge source like Wikipedia. Here we decompose this problem into two parts: an entity linking task (retrieving relative Wikipedia pages) and recognizing textual entailment between the claim and selected pages. In this paper, we present an end-to-end multi-task learning with bi-direction attention (EMBA) model to classify the claim as {\textquotedblleft}supports{\textquotedblright}, {\textquotedblleft}refutes{\textquotedblright} or {\textquotedblleft}not enough info{\textquotedblright} with respect to the pages retrieved and detect sentences as evidence at the same time. We conduct experiments on the FEVER (Fact Extraction and VERification) paper test dataset and shared task test dataset, a new public dataset for verification against textual sources. Experimental results show that our method achieves comparable performance compared with the baseline system."
}