@inproceedings{larson-etal-2020-iterative,
title = "Iterative Feature Mining for Constraint-Based Data Collection to Increase Data Diversity and Model Robustness",
author = "Larson, Stefan and
Zheng, Anthony and
Mahendran, Anish and
Tekriwal, Rishi and
Cheung, Adrian and
Guldan, Eric and
Leach, Kevin and
Kummerfeld, Jonathan K.",
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.650",
doi = "10.18653/v1/2020.emnlp-main.650",
pages = "8097--8106",
abstract = "Diverse data is crucial for training robust models, but crowdsourced text often lacks diversity as workers tend to write simple variations from prompts. We propose a general approach for guiding workers to write more diverse text by iteratively constraining their writing. We show how prior workflows are special cases of our approach, and present a way to apply the approach to dialog tasks such as intent classification and slot-filling. Using our method, we create more challenging versions of test sets from prior dialog datasets and find dramatic performance drops for standard models. Finally, we show that our approach is complementary to recent work on improving data diversity, and training on data collected with our approach leads to more robust models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="larson-etal-2020-iterative">
<titleInfo>
<title>Iterative Feature Mining for Constraint-Based Data Collection to Increase Data Diversity and Model Robustness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Larson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anish</namePart>
<namePart type="family">Mahendran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishi</namePart>
<namePart type="family">Tekriwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Guldan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Leach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Kummerfeld</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>Diverse data is crucial for training robust models, but crowdsourced text often lacks diversity as workers tend to write simple variations from prompts. We propose a general approach for guiding workers to write more diverse text by iteratively constraining their writing. We show how prior workflows are special cases of our approach, and present a way to apply the approach to dialog tasks such as intent classification and slot-filling. Using our method, we create more challenging versions of test sets from prior dialog datasets and find dramatic performance drops for standard models. Finally, we show that our approach is complementary to recent work on improving data diversity, and training on data collected with our approach leads to more robust models.</abstract>
<identifier type="citekey">larson-etal-2020-iterative</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.650</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.650</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8097</start>
<end>8106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Iterative Feature Mining for Constraint-Based Data Collection to Increase Data Diversity and Model Robustness
%A Larson, Stefan
%A Zheng, Anthony
%A Mahendran, Anish
%A Tekriwal, Rishi
%A Cheung, Adrian
%A Guldan, Eric
%A Leach, Kevin
%A Kummerfeld, Jonathan K.
%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 larson-etal-2020-iterative
%X Diverse data is crucial for training robust models, but crowdsourced text often lacks diversity as workers tend to write simple variations from prompts. We propose a general approach for guiding workers to write more diverse text by iteratively constraining their writing. We show how prior workflows are special cases of our approach, and present a way to apply the approach to dialog tasks such as intent classification and slot-filling. Using our method, we create more challenging versions of test sets from prior dialog datasets and find dramatic performance drops for standard models. Finally, we show that our approach is complementary to recent work on improving data diversity, and training on data collected with our approach leads to more robust models.
%R 10.18653/v1/2020.emnlp-main.650
%U https://aclanthology.org/2020.emnlp-main.650
%U https://doi.org/10.18653/v1/2020.emnlp-main.650
%P 8097-8106
Markdown (Informal)
[Iterative Feature Mining for Constraint-Based Data Collection to Increase Data Diversity and Model Robustness](https://aclanthology.org/2020.emnlp-main.650) (Larson et al., EMNLP 2020)
ACL