@inproceedings{yang-etal-2019-predicting,
title = "Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction",
author = "Yang, Yinfei and
Agarwal, Oshin and
Tar, Chris and
Wallace, Byron C. and
Nenkova, Ani",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1150",
doi = "10.18653/v1/N19-1150",
pages = "1471--1480",
abstract = "Modern NLP systems require high-quality annotated data. For specialized domains, expert annotations may be prohibitively expensive; the alternative is to rely on crowdsourcing to reduce costs at the risk of introducing noise. In this paper we demonstrate that directly modeling instance difficulty can be used to improve model performance and to route instances to appropriate annotators. Our difficulty prediction model combines two learned representations: a {`}universal{'} encoder trained on out of domain data, and a task-specific encoder. Experiments on a complex biomedical information extraction task using expert and lay annotators show that: (i) simply excluding from the training data instances predicted to be difficult yields a small boost in performance; (ii) using difficulty scores to weight instances during training provides further, consistent gains; (iii) assigning instances predicted to be difficult to domain experts is an effective strategy for task routing. Further, our experiments confirm the expectation that for such domain-specific tasks expert annotations are of much higher quality and preferable to obtain if practical and that augmenting small amounts of expert data with a larger set of lay annotations leads to further improvements in model performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2019-predicting">
<titleInfo>
<title>Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinfei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oshin</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Tar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byron</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Wallace</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ani</namePart>
<namePart type="family">Nenkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modern NLP systems require high-quality annotated data. For specialized domains, expert annotations may be prohibitively expensive; the alternative is to rely on crowdsourcing to reduce costs at the risk of introducing noise. In this paper we demonstrate that directly modeling instance difficulty can be used to improve model performance and to route instances to appropriate annotators. Our difficulty prediction model combines two learned representations: a ‘universal’ encoder trained on out of domain data, and a task-specific encoder. Experiments on a complex biomedical information extraction task using expert and lay annotators show that: (i) simply excluding from the training data instances predicted to be difficult yields a small boost in performance; (ii) using difficulty scores to weight instances during training provides further, consistent gains; (iii) assigning instances predicted to be difficult to domain experts is an effective strategy for task routing. Further, our experiments confirm the expectation that for such domain-specific tasks expert annotations are of much higher quality and preferable to obtain if practical and that augmenting small amounts of expert data with a larger set of lay annotations leads to further improvements in model performance.</abstract>
<identifier type="citekey">yang-etal-2019-predicting</identifier>
<identifier type="doi">10.18653/v1/N19-1150</identifier>
<location>
<url>https://aclanthology.org/N19-1150</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1471</start>
<end>1480</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction
%A Yang, Yinfei
%A Agarwal, Oshin
%A Tar, Chris
%A Wallace, Byron C.
%A Nenkova, Ani
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F yang-etal-2019-predicting
%X Modern NLP systems require high-quality annotated data. For specialized domains, expert annotations may be prohibitively expensive; the alternative is to rely on crowdsourcing to reduce costs at the risk of introducing noise. In this paper we demonstrate that directly modeling instance difficulty can be used to improve model performance and to route instances to appropriate annotators. Our difficulty prediction model combines two learned representations: a ‘universal’ encoder trained on out of domain data, and a task-specific encoder. Experiments on a complex biomedical information extraction task using expert and lay annotators show that: (i) simply excluding from the training data instances predicted to be difficult yields a small boost in performance; (ii) using difficulty scores to weight instances during training provides further, consistent gains; (iii) assigning instances predicted to be difficult to domain experts is an effective strategy for task routing. Further, our experiments confirm the expectation that for such domain-specific tasks expert annotations are of much higher quality and preferable to obtain if practical and that augmenting small amounts of expert data with a larger set of lay annotations leads to further improvements in model performance.
%R 10.18653/v1/N19-1150
%U https://aclanthology.org/N19-1150
%U https://doi.org/10.18653/v1/N19-1150
%P 1471-1480
Markdown (Informal)
[Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction](https://aclanthology.org/N19-1150) (Yang et al., NAACL 2019)
ACL