@inproceedings{rawat-etal-2025-encoder,
title = "Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight {GPT} in Astronomy Knowledge Extraction",
author = "Rawat, Shivam and
Flek, Lucie and
Karimi, Akbar",
editor = "Accomazzi, Alberto and
Ghosal, Tirthankar and
Grezes, Felix and
Lockhart, Kelly",
booktitle = "Proceedings of the Third Workshop for Artificial Intelligence for Scientific Publications",
month = dec,
year = "2025",
address = "Mumbai, India and virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wasp-main.22/",
pages = "195--200",
ISBN = "979-8-89176-310-4",
abstract = "Scientific literature in astronomy is rapidly expanding, making it increasingly important to automate the extraction of key entities and contextual information from research papers. In this paper, we present an encoder-based system for extracting knowledge from astronomy articles. Our objective is to develop models capable of classifying telescope references, detecting auxiliary semantic attributes, and recognizing instrument mentions from textual content. To this end, we implement a multi-task transformer-based system built upon the SciBERT model and fine-tuned for astronomy corpora classification. To carry out the fine-tuning, we stochastically sample segments from the training data and use majority voting over the test segments at inference time. Our system, despite its simplicity and low-cost implementation, significantly outperforms the open-weight GPT baseline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rawat-etal-2025-encoder">
<titleInfo>
<title>Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivam</namePart>
<namePart type="family">Rawat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akbar</namePart>
<namePart type="family">Karimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop for Artificial Intelligence for Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Accomazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Felix</namePart>
<namePart type="family">Grezes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Lockhart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India and virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-310-4</identifier>
</relatedItem>
<abstract>Scientific literature in astronomy is rapidly expanding, making it increasingly important to automate the extraction of key entities and contextual information from research papers. In this paper, we present an encoder-based system for extracting knowledge from astronomy articles. Our objective is to develop models capable of classifying telescope references, detecting auxiliary semantic attributes, and recognizing instrument mentions from textual content. To this end, we implement a multi-task transformer-based system built upon the SciBERT model and fine-tuned for astronomy corpora classification. To carry out the fine-tuning, we stochastically sample segments from the training data and use majority voting over the test segments at inference time. Our system, despite its simplicity and low-cost implementation, significantly outperforms the open-weight GPT baseline.</abstract>
<identifier type="citekey">rawat-etal-2025-encoder</identifier>
<location>
<url>https://aclanthology.org/2025.wasp-main.22/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>195</start>
<end>200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction
%A Rawat, Shivam
%A Flek, Lucie
%A Karimi, Akbar
%Y Accomazzi, Alberto
%Y Ghosal, Tirthankar
%Y Grezes, Felix
%Y Lockhart, Kelly
%S Proceedings of the Third Workshop for Artificial Intelligence for Scientific Publications
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India and virtual
%@ 979-8-89176-310-4
%F rawat-etal-2025-encoder
%X Scientific literature in astronomy is rapidly expanding, making it increasingly important to automate the extraction of key entities and contextual information from research papers. In this paper, we present an encoder-based system for extracting knowledge from astronomy articles. Our objective is to develop models capable of classifying telescope references, detecting auxiliary semantic attributes, and recognizing instrument mentions from textual content. To this end, we implement a multi-task transformer-based system built upon the SciBERT model and fine-tuned for astronomy corpora classification. To carry out the fine-tuning, we stochastically sample segments from the training data and use majority voting over the test segments at inference time. Our system, despite its simplicity and low-cost implementation, significantly outperforms the open-weight GPT baseline.
%U https://aclanthology.org/2025.wasp-main.22/
%P 195-200
Markdown (Informal)
[Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction](https://aclanthology.org/2025.wasp-main.22/) (Rawat et al., WASP 2025)
ACL