@inproceedings{zhang-etal-2023-causal-matching,
title = "Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies",
author = "Zhang, Raymond and
Kennard, Neha Nayak and
Smith, Daniel and
McFarland, Daniel and
McCallum, Andrew and
Keith, Katherine",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.83",
doi = "10.18653/v1/2023.findings-acl.83",
pages = "1284--1297",
abstract = "A promising approach to estimate the causal effects of peer review policies is to analyze data from publication venues that shift policies from single-blind to double-blind from one year to the next. However, in these settings the content of the manuscript is a confounding variable{---}each year has a different distribution of scientific content which may naturally affect the distribution of reviewer scores. To address this textual confounding, we extend variable ratio nearest neighbor matching to incorporate text embeddings. We compare this matching method to a widely-used causal method of stratified propensity score matching and a baseline of randomly selected matches. For our case study of the ICLR conference shifting from single- to double-blind review from 2017 to 2018, we find human judges prefer manuscript matches from our method in 70{\%} of cases. While the unadjusted estimate of the average causal effect of reviewers{'} scores is -0.25, our method shifts the estimate to -0.17, a slightly smaller difference between the outcomes of single- and double-blind policies. We hope this case study enables exploration of additional text-based causal estimation methods and domains in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-causal-matching">
<titleInfo>
<title>Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neha</namePart>
<namePart type="given">Nayak</namePart>
<namePart type="family">Kennard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">McFarland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A promising approach to estimate the causal effects of peer review policies is to analyze data from publication venues that shift policies from single-blind to double-blind from one year to the next. However, in these settings the content of the manuscript is a confounding variable—each year has a different distribution of scientific content which may naturally affect the distribution of reviewer scores. To address this textual confounding, we extend variable ratio nearest neighbor matching to incorporate text embeddings. We compare this matching method to a widely-used causal method of stratified propensity score matching and a baseline of randomly selected matches. For our case study of the ICLR conference shifting from single- to double-blind review from 2017 to 2018, we find human judges prefer manuscript matches from our method in 70% of cases. While the unadjusted estimate of the average causal effect of reviewers’ scores is -0.25, our method shifts the estimate to -0.17, a slightly smaller difference between the outcomes of single- and double-blind policies. We hope this case study enables exploration of additional text-based causal estimation methods and domains in the future.</abstract>
<identifier type="citekey">zhang-etal-2023-causal-matching</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.83</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.83</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1284</start>
<end>1297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies
%A Zhang, Raymond
%A Kennard, Neha Nayak
%A Smith, Daniel
%A McFarland, Daniel
%A McCallum, Andrew
%A Keith, Katherine
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhang-etal-2023-causal-matching
%X A promising approach to estimate the causal effects of peer review policies is to analyze data from publication venues that shift policies from single-blind to double-blind from one year to the next. However, in these settings the content of the manuscript is a confounding variable—each year has a different distribution of scientific content which may naturally affect the distribution of reviewer scores. To address this textual confounding, we extend variable ratio nearest neighbor matching to incorporate text embeddings. We compare this matching method to a widely-used causal method of stratified propensity score matching and a baseline of randomly selected matches. For our case study of the ICLR conference shifting from single- to double-blind review from 2017 to 2018, we find human judges prefer manuscript matches from our method in 70% of cases. While the unadjusted estimate of the average causal effect of reviewers’ scores is -0.25, our method shifts the estimate to -0.17, a slightly smaller difference between the outcomes of single- and double-blind policies. We hope this case study enables exploration of additional text-based causal estimation methods and domains in the future.
%R 10.18653/v1/2023.findings-acl.83
%U https://aclanthology.org/2023.findings-acl.83
%U https://doi.org/10.18653/v1/2023.findings-acl.83
%P 1284-1297
Markdown (Informal)
[Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies](https://aclanthology.org/2023.findings-acl.83) (Zhang et al., Findings 2023)
ACL