@inproceedings{khoury-etal-2020-vector,
    title = "Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in {NLP} Applications",
    author = "Khoury, Matthew  and
      Dangovski, Rumen  and
      Ou, Longwu  and
      Nakov, Preslav  and
      Shen, Yichen  and
      Jing, Li",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.emnlp-main.640/",
    doi = "10.18653/v1/2020.emnlp-main.640",
    pages = "7975--7984"
}