@inproceedings{panapitiya-etal-2021-extracting,
title = "Extracting Material Property Measurement Data from Scientific Articles",
author = "Panapitiya, Gihan and
Parks, Fred and
Sepulveda, Jonathan and
Saldanha, Emily",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.438",
doi = "10.18653/v1/2021.emnlp-main.438",
pages = "5393--5402",
abstract = "Machine learning-based prediction of material properties is often hampered by the lack of sufficiently large training data sets. The majority of such measurement data is embedded in scientific literature and the ability to automatically extract these data is essential to support the development of reliable property prediction methods. In this work, we describe a methodology for developing an automatic property extraction framework using material solubility as the target property. We create a training and evaluation data set containing tags for solubility-related entities using a combination of regular expressions and manual tagging. We then compare five entity recognition models leveraging both token-level and span-level architectures on the task of classifying solute names, solubility values, and solubility units. Additionally, we explore a novel pretraining approach that leverages automated chemical name and quantity extraction tools to generate large datasets that do not rely on intensive manual tagging. Finally, we perform an analysis to identify the causes of classification errors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="panapitiya-etal-2021-extracting">
<titleInfo>
<title>Extracting Material Property Measurement Data from Scientific Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gihan</namePart>
<namePart type="family">Panapitiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Parks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Sepulveda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Saldanha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine learning-based prediction of material properties is often hampered by the lack of sufficiently large training data sets. The majority of such measurement data is embedded in scientific literature and the ability to automatically extract these data is essential to support the development of reliable property prediction methods. In this work, we describe a methodology for developing an automatic property extraction framework using material solubility as the target property. We create a training and evaluation data set containing tags for solubility-related entities using a combination of regular expressions and manual tagging. We then compare five entity recognition models leveraging both token-level and span-level architectures on the task of classifying solute names, solubility values, and solubility units. Additionally, we explore a novel pretraining approach that leverages automated chemical name and quantity extraction tools to generate large datasets that do not rely on intensive manual tagging. Finally, we perform an analysis to identify the causes of classification errors.</abstract>
<identifier type="citekey">panapitiya-etal-2021-extracting</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.438</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.438</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>5393</start>
<end>5402</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting Material Property Measurement Data from Scientific Articles
%A Panapitiya, Gihan
%A Parks, Fred
%A Sepulveda, Jonathan
%A Saldanha, Emily
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F panapitiya-etal-2021-extracting
%X Machine learning-based prediction of material properties is often hampered by the lack of sufficiently large training data sets. The majority of such measurement data is embedded in scientific literature and the ability to automatically extract these data is essential to support the development of reliable property prediction methods. In this work, we describe a methodology for developing an automatic property extraction framework using material solubility as the target property. We create a training and evaluation data set containing tags for solubility-related entities using a combination of regular expressions and manual tagging. We then compare five entity recognition models leveraging both token-level and span-level architectures on the task of classifying solute names, solubility values, and solubility units. Additionally, we explore a novel pretraining approach that leverages automated chemical name and quantity extraction tools to generate large datasets that do not rely on intensive manual tagging. Finally, we perform an analysis to identify the causes of classification errors.
%R 10.18653/v1/2021.emnlp-main.438
%U https://aclanthology.org/2021.emnlp-main.438
%U https://doi.org/10.18653/v1/2021.emnlp-main.438
%P 5393-5402
Markdown (Informal)
[Extracting Material Property Measurement Data from Scientific Articles](https://aclanthology.org/2021.emnlp-main.438) (Panapitiya et al., EMNLP 2021)
ACL