@inproceedings{salhofer-etal-2022-impact,
title = "Impact of Training Instance Selection on Domain-Specific Entity Extraction using {BERT}",
author = "Salhofer, Eileen and
Liu, Xing Lan and
Kern, Roman",
editor = "Ippolito, Daphne and
Li, Liunian Harold and
Pacheco, Maria Leonor and
Chen, Danqi and
Xue, Nianwen",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-srw.11",
doi = "10.18653/v1/2022.naacl-srw.11",
pages = "83--88",
abstract = "State of the art performances for entity extraction tasks are achieved by supervised learning, specifically, by fine-tuning pretrained language models such as BERT. As a result, annotating application specific data is the first step in many use cases. However, no practical guidelines are available for annotation requirements. This work supports practitioners by empirically answering the frequently asked questions (1) how many training samples to annotate? (2) which examples to annotate? We found that BERT achieves up to 80{\%} F1 when fine-tuned on only 70 training examples, especially on biomedical domain. The key features for guiding the selection of high performing training instances are identified to be pseudo-perplexity and sentence-length. The best training dataset constructed using our proposed selection strategy shows F1 score that is equivalent to a random selection with twice the sample size. The requirement of only a small number of training data implies cheaper implementations and opens door to wider range of applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salhofer-etal-2022-impact">
<titleInfo>
<title>Impact of Training Instance Selection on Domain-Specific Entity Extraction using BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eileen</namePart>
<namePart type="family">Salhofer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="given">Lan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Kern</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daphne</namePart>
<namePart type="family">Ippolito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liunian</namePart>
<namePart type="given">Harold</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Leonor</namePart>
<namePart type="family">Pacheco</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">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>State of the art performances for entity extraction tasks are achieved by supervised learning, specifically, by fine-tuning pretrained language models such as BERT. As a result, annotating application specific data is the first step in many use cases. However, no practical guidelines are available for annotation requirements. This work supports practitioners by empirically answering the frequently asked questions (1) how many training samples to annotate? (2) which examples to annotate? We found that BERT achieves up to 80% F1 when fine-tuned on only 70 training examples, especially on biomedical domain. The key features for guiding the selection of high performing training instances are identified to be pseudo-perplexity and sentence-length. The best training dataset constructed using our proposed selection strategy shows F1 score that is equivalent to a random selection with twice the sample size. The requirement of only a small number of training data implies cheaper implementations and opens door to wider range of applications.</abstract>
<identifier type="citekey">salhofer-etal-2022-impact</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-srw.11</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-srw.11</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>83</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Impact of Training Instance Selection on Domain-Specific Entity Extraction using BERT
%A Salhofer, Eileen
%A Liu, Xing Lan
%A Kern, Roman
%Y Ippolito, Daphne
%Y Li, Liunian Harold
%Y Pacheco, Maria Leonor
%Y Chen, Danqi
%Y Xue, Nianwen
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F salhofer-etal-2022-impact
%X State of the art performances for entity extraction tasks are achieved by supervised learning, specifically, by fine-tuning pretrained language models such as BERT. As a result, annotating application specific data is the first step in many use cases. However, no practical guidelines are available for annotation requirements. This work supports practitioners by empirically answering the frequently asked questions (1) how many training samples to annotate? (2) which examples to annotate? We found that BERT achieves up to 80% F1 when fine-tuned on only 70 training examples, especially on biomedical domain. The key features for guiding the selection of high performing training instances are identified to be pseudo-perplexity and sentence-length. The best training dataset constructed using our proposed selection strategy shows F1 score that is equivalent to a random selection with twice the sample size. The requirement of only a small number of training data implies cheaper implementations and opens door to wider range of applications.
%R 10.18653/v1/2022.naacl-srw.11
%U https://aclanthology.org/2022.naacl-srw.11
%U https://doi.org/10.18653/v1/2022.naacl-srw.11
%P 83-88
Markdown (Informal)
[Impact of Training Instance Selection on Domain-Specific Entity Extraction using BERT](https://aclanthology.org/2022.naacl-srw.11) (Salhofer et al., NAACL 2022)
ACL