@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://aclanthology.org/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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mass-roitman-2020-ad">
<titleInfo>
<title>Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yosi</namePart>
<namePart type="family">Mass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haggai</namePart>
<namePart type="family">Roitman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">mass-roitman-2020-ad</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.343</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.343</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4191</start>
<end>4197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2
%A Mass, Yosi
%A Roitman, Haggai
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F mass-roitman-2020-ad
%X 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.
%R 10.18653/v1/2020.emnlp-main.343
%U https://aclanthology.org/2020.emnlp-main.343
%U https://doi.org/10.18653/v1/2020.emnlp-main.343
%P 4191-4197
Markdown (Informal)
[Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2](https://aclanthology.org/2020.emnlp-main.343) (Mass & Roitman, EMNLP 2020)
ACL