@inproceedings{mass-roitman-2020-ad,
    title = "Ad-hoc Document Retrieval using Weak-Supervision with {BERT} and {GPT}2",
    author = "Mass, Yosi  and
      Roitman, Haggai",
    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/add-emnlp-2024-awards/2020.emnlp-main.343/",
    doi = "10.18653/v1/2020.emnlp-main.343",
    pages = "4191--4197",
    abstract = "We describe a weakly-supervised method for training deep learning models for the task of ad-hoc document retrieval. Our method is based on generative and discriminative models that are trained using weak-supervision just from the documents in the corpus. We present an end-to-end retrieval system that starts with traditional information retrieval methods, followed by two deep learning re-rankers. We evaluate our method on three different datasets: a COVID-19 related scientific literature dataset and two news datasets. We show that our method outperforms state-of-the-art methods; this without the need for the expensive process of manually labeling data."
}