@inproceedings{balachandran-etal-2021-simple,
title = "Simple and Efficient ways to Improve {REALM}",
author = "Balachandran, Vidhisha and
Vaswani, Ashish and
Tsvetkov, Yulia and
Parmar, Niki",
editor = "Fisch, Adam and
Talmor, Alon and
Chen, Danqi and
Choi, Eunsol and
Seo, Minjoon and
Lewis, Patrick and
Jia, Robin and
Min, Sewon",
booktitle = "Proceedings of the 3rd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrqa-1.16",
doi = "10.18653/v1/2021.mrqa-1.16",
pages = "158--164",
abstract = "Dense retrieval has been shown to be effective for Open Domain Question Answering, surpassing sparse retrieval methods like BM25. One such model, REALM, (Guu et al., 2020) is an end-to-end dense retrieval system that uses MLM based pretraining for improved downstream QA performance. However, the current REALM setup uses limited resources and is not comparable in scale to more recent systems, contributing to its lower performance. Additionally, it relies on noisy supervision for retrieval during fine-tuning. We propose REALM++, where we improve upon the training and inference setups and introduce better supervision signal for improving performance, without any architectural changes. REALM++ achieves {\textasciitilde}5.5{\%} absolute accuracy gains over the baseline while being faster to train. It also matches the performance of large models which have 3x more parameters demonstrating the efficiency of our setup.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balachandran-etal-2021-simple">
<titleInfo>
<title>Simple and Efficient ways to Improve REALM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Vaswani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niki</namePart>
<namePart type="family">Parmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dense retrieval has been shown to be effective for Open Domain Question Answering, surpassing sparse retrieval methods like BM25. One such model, REALM, (Guu et al., 2020) is an end-to-end dense retrieval system that uses MLM based pretraining for improved downstream QA performance. However, the current REALM setup uses limited resources and is not comparable in scale to more recent systems, contributing to its lower performance. Additionally, it relies on noisy supervision for retrieval during fine-tuning. We propose REALM++, where we improve upon the training and inference setups and introduce better supervision signal for improving performance, without any architectural changes. REALM++ achieves ~5.5% absolute accuracy gains over the baseline while being faster to train. It also matches the performance of large models which have 3x more parameters demonstrating the efficiency of our setup.</abstract>
<identifier type="citekey">balachandran-etal-2021-simple</identifier>
<identifier type="doi">10.18653/v1/2021.mrqa-1.16</identifier>
<location>
<url>https://aclanthology.org/2021.mrqa-1.16</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>158</start>
<end>164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple and Efficient ways to Improve REALM
%A Balachandran, Vidhisha
%A Vaswani, Ashish
%A Tsvetkov, Yulia
%A Parmar, Niki
%Y Fisch, Adam
%Y Talmor, Alon
%Y Chen, Danqi
%Y Choi, Eunsol
%Y Seo, Minjoon
%Y Lewis, Patrick
%Y Jia, Robin
%Y Min, Sewon
%S Proceedings of the 3rd Workshop on Machine Reading for Question Answering
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F balachandran-etal-2021-simple
%X Dense retrieval has been shown to be effective for Open Domain Question Answering, surpassing sparse retrieval methods like BM25. One such model, REALM, (Guu et al., 2020) is an end-to-end dense retrieval system that uses MLM based pretraining for improved downstream QA performance. However, the current REALM setup uses limited resources and is not comparable in scale to more recent systems, contributing to its lower performance. Additionally, it relies on noisy supervision for retrieval during fine-tuning. We propose REALM++, where we improve upon the training and inference setups and introduce better supervision signal for improving performance, without any architectural changes. REALM++ achieves ~5.5% absolute accuracy gains over the baseline while being faster to train. It also matches the performance of large models which have 3x more parameters demonstrating the efficiency of our setup.
%R 10.18653/v1/2021.mrqa-1.16
%U https://aclanthology.org/2021.mrqa-1.16
%U https://doi.org/10.18653/v1/2021.mrqa-1.16
%P 158-164
Markdown (Informal)
[Simple and Efficient ways to Improve REALM](https://aclanthology.org/2021.mrqa-1.16) (Balachandran et al., MRQA 2021)
ACL
- Vidhisha Balachandran, Ashish Vaswani, Yulia Tsvetkov, and Niki Parmar. 2021. Simple and Efficient ways to Improve REALM. In Proceedings of the 3rd Workshop on Machine Reading for Question Answering, pages 158–164, Punta Cana, Dominican Republic. Association for Computational Linguistics.