@inproceedings{miller-etal-2021-domain,
title = "Domain adaptation in practice: Lessons from a real-world information extraction pipeline",
author = "Miller, Timothy and
Laparra, Egoitz and
Bethard, Steven",
editor = "Ben-David, Eyal and
Cohen, Shay and
McDonald, Ryan and
Plank, Barbara and
Reichart, Roi and
Rotman, Guy and
Ziser, Yftah",
booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
month = apr,
year = "2021",
address = "Kyiv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.adaptnlp-1.11/",
pages = "105--110",
abstract = "Advances in transfer learning and domain adaptation have raised hopes that once-challenging NLP tasks are ready to be put to use for sophisticated information extraction needs. In this work, we describe an effort to do just that {--} combining state-of-the-art neural methods for negation detection, document time relation extraction, and aspectual link prediction, with the eventual goal of extracting drug timelines from electronic health record text. We train on the THYME colon cancer corpus and test on both the THYME brain cancer corpus and an internal corpus, and show that performance of the combined systems is unacceptable despite good performance of individual systems. Although domain adaptation shows improvements on each individual system, the model selection problem is a barrier to improving overall pipeline performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miller-etal-2021-domain">
<titleInfo>
<title>Domain adaptation in practice: Lessons from a real-world information extraction pipeline</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Egoitz</namePart>
<namePart type="family">Laparra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Domain Adaptation for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eyal</namePart>
<namePart type="family">Ben-David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">McDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Rotman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yftah</namePart>
<namePart type="family">Ziser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Advances in transfer learning and domain adaptation have raised hopes that once-challenging NLP tasks are ready to be put to use for sophisticated information extraction needs. In this work, we describe an effort to do just that – combining state-of-the-art neural methods for negation detection, document time relation extraction, and aspectual link prediction, with the eventual goal of extracting drug timelines from electronic health record text. We train on the THYME colon cancer corpus and test on both the THYME brain cancer corpus and an internal corpus, and show that performance of the combined systems is unacceptable despite good performance of individual systems. Although domain adaptation shows improvements on each individual system, the model selection problem is a barrier to improving overall pipeline performance.</abstract>
<identifier type="citekey">miller-etal-2021-domain</identifier>
<location>
<url>https://aclanthology.org/2021.adaptnlp-1.11/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>105</start>
<end>110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain adaptation in practice: Lessons from a real-world information extraction pipeline
%A Miller, Timothy
%A Laparra, Egoitz
%A Bethard, Steven
%Y Ben-David, Eyal
%Y Cohen, Shay
%Y McDonald, Ryan
%Y Plank, Barbara
%Y Reichart, Roi
%Y Rotman, Guy
%Y Ziser, Yftah
%S Proceedings of the Second Workshop on Domain Adaptation for NLP
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine
%F miller-etal-2021-domain
%X Advances in transfer learning and domain adaptation have raised hopes that once-challenging NLP tasks are ready to be put to use for sophisticated information extraction needs. In this work, we describe an effort to do just that – combining state-of-the-art neural methods for negation detection, document time relation extraction, and aspectual link prediction, with the eventual goal of extracting drug timelines from electronic health record text. We train on the THYME colon cancer corpus and test on both the THYME brain cancer corpus and an internal corpus, and show that performance of the combined systems is unacceptable despite good performance of individual systems. Although domain adaptation shows improvements on each individual system, the model selection problem is a barrier to improving overall pipeline performance.
%U https://aclanthology.org/2021.adaptnlp-1.11/
%P 105-110
Markdown (Informal)
[Domain adaptation in practice: Lessons from a real-world information extraction pipeline](https://aclanthology.org/2021.adaptnlp-1.11/) (Miller et al., AdaptNLP 2021)
ACL