@inproceedings{ohsugi-etal-2019-simple,
    title = "A Simple but Effective Method to Incorporate Multi-turn Context with {BERT} for Conversational Machine Comprehension",
    author = "Ohsugi, Yasuhito  and
      Saito, Itsumi  and
      Nishida, Kyosuke  and
      Asano, Hisako  and
      Tomita, Junji",
    editor = "Chen, Yun-Nung  and
      Bedrax-Weiss, Tania  and
      Hakkani-Tur, Dilek  and
      Kumar, Anuj  and
      Lewis, Mike  and
      Luong, Thang-Minh  and
      Su, Pei-Hao  and
      Wen, Tsung-Hsien",
    booktitle = "Proceedings of the First Workshop on NLP for Conversational AI",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W19-4102",
    doi = "10.18653/v1/W19-4102",
    pages = "11--17",
    abstract = "Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pretraining language model, has been successful for single-turn machine comprehension, while modeling multiple turns of question answering with BERT has not been established because BERT has a limit on the number and the length of input sequences. In this paper, we propose a simple but effective method with BERT for CMC. Our method uses BERT to encode a paragraph independently conditioned with each question and each answer in a multi-turn context. Then, the method predicts an answer on the basis of the paragraph representations encoded with BERT. The experiments with representative CMC datasets, QuAC and CoQA, show that our method outperformed recently published methods (+0.8 F1 on QuAC and +2.1 F1 on CoQA). In addition, we conducted a detailed analysis of the effects of the number and types of dialogue history on the accuracy of CMC, and we found that the gold answer history, which may not be given in an actual conversation, contributed to the model performance most on both datasets.",
}