@inproceedings{song-etal-2024-metadata,
title = "Metadata Enhancement Using Large Language Models",
author = "Song, Hyunju and
Bethard, Steven and
Thomer, Andrea",
editor = "Ghosal, Tirthankar and
Singh, Amanpreet and
Waard, Anita and
Mayr, Philipp and
Naik, Aakanksha and
Weller, Orion and
Lee, Yoonjoo and
Shen, Shannon and
Qin, Yanxia",
booktitle = "Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sdp-1.14",
pages = "145--154",
abstract = "In the natural sciences, a common form of scholarly document is a physical sample record, which provides categorical and textual metadata for specimens collected and analyzed for scientific research. Physical sample archives like museums and repositories publish these records in data repositories to support reproducible science and enable the discovery of physical samples. However, the success of resource discovery in such interfaces depends on the completeness of the sample records. We investigate approaches for automatically completing the scientific metadata fields of sample records. We apply large language models in zero and few-shot settings and incorporate the hierarchical structure of the taxonomy. We show that a combination of record summarization, bottom-up taxonomy traversal, and few-shot prompting yield F1 as high as 0.928 on metadata completion in the Earth science domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2024-metadata">
<titleInfo>
<title>Metadata Enhancement Using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyunju</namePart>
<namePart type="family">Song</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>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Thomer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orion</namePart>
<namePart type="family">Weller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonjoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shannon</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanxia</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the natural sciences, a common form of scholarly document is a physical sample record, which provides categorical and textual metadata for specimens collected and analyzed for scientific research. Physical sample archives like museums and repositories publish these records in data repositories to support reproducible science and enable the discovery of physical samples. However, the success of resource discovery in such interfaces depends on the completeness of the sample records. We investigate approaches for automatically completing the scientific metadata fields of sample records. We apply large language models in zero and few-shot settings and incorporate the hierarchical structure of the taxonomy. We show that a combination of record summarization, bottom-up taxonomy traversal, and few-shot prompting yield F1 as high as 0.928 on metadata completion in the Earth science domain.</abstract>
<identifier type="citekey">song-etal-2024-metadata</identifier>
<location>
<url>https://aclanthology.org/2024.sdp-1.14</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>145</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Metadata Enhancement Using Large Language Models
%A Song, Hyunju
%A Bethard, Steven
%A Thomer, Andrea
%Y Ghosal, Tirthankar
%Y Singh, Amanpreet
%Y Waard, Anita
%Y Mayr, Philipp
%Y Naik, Aakanksha
%Y Weller, Orion
%Y Lee, Yoonjoo
%Y Shen, Shannon
%Y Qin, Yanxia
%S Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F song-etal-2024-metadata
%X In the natural sciences, a common form of scholarly document is a physical sample record, which provides categorical and textual metadata for specimens collected and analyzed for scientific research. Physical sample archives like museums and repositories publish these records in data repositories to support reproducible science and enable the discovery of physical samples. However, the success of resource discovery in such interfaces depends on the completeness of the sample records. We investigate approaches for automatically completing the scientific metadata fields of sample records. We apply large language models in zero and few-shot settings and incorporate the hierarchical structure of the taxonomy. We show that a combination of record summarization, bottom-up taxonomy traversal, and few-shot prompting yield F1 as high as 0.928 on metadata completion in the Earth science domain.
%U https://aclanthology.org/2024.sdp-1.14
%P 145-154
Markdown (Informal)
[Metadata Enhancement Using Large Language Models](https://aclanthology.org/2024.sdp-1.14) (Song et al., sdp-WS 2024)
ACL
- Hyunju Song, Steven Bethard, and Andrea Thomer. 2024. Metadata Enhancement Using Large Language Models. In Proceedings of the Fourth Workshop on Scholarly Document Processing (SDP 2024), pages 145–154, Bangkok, Thailand. Association for Computational Linguistics.