@inproceedings{yu-etal-2020-crossing,
    title = "Crossing Variational Autoencoders for Answer Retrieval",
    author = "Yu, Wenhao  and
      Wu, Lingfei  and
      Zeng, Qingkai  and
      Tao, Shu  and
      Deng, Yu  and
      Jiang, Meng",
    editor = "Jurafsky, Dan  and
      Chai, Joyce  and
      Schluter, Natalie  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.acl-main.498",
    doi = "10.18653/v1/2020.acl-main.498",
    pages = "5635--5641",
    abstract = "Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semantics between question and answer. In this work, we propose to cross variational auto-encoders by generating questions with aligned answers and generating answers with aligned questions. Experiments show that our method outperforms the state-of-the-art answer retrieval method on SQuAD.",
}