%0 Conference Proceedings %T Crossing Variational Autoencoders for Answer Retrieval %A Yu, Wenhao %A Wu, Lingfei %A Zeng, Qingkai %A Tao, Shu %A Deng, Yu %A Jiang, Meng %Y Jurafsky, Dan %Y Chai, Joyce %Y Schluter, Natalie %Y Tetreault, Joel %S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics %D 2020 %8 July %I Association for Computational Linguistics %C Online %F yu-etal-2020-crossing %X 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. %R 10.18653/v1/2020.acl-main.498 %U https://aclanthology.org/2020.acl-main.498 %U https://doi.org/10.18653/v1/2020.acl-main.498 %P 5635-5641