@inproceedings{singh-singh-2024-cosaemb,
title = "{C}o{SAE}mb: Contrastive Section-aware Aspect Embeddings for Scientific Articles",
author = "Singh, Shruti and
Singh, Mayank",
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-1.27",
pages = "283--292",
abstract = "Research papers are long documents that contain information about various aspects such as background, prior work, methodology, and results. Existing works on scientific document representation learning only leverage the title and abstract of the paper. We present CoSAEmb, a model that learns representations from the full text of 97402 scientific papers from the S2ORC dataset. We present a novel supervised contrastive training framework for long documents using triplet loss and margin gradation. Our framework can be used to learn representations of long documents with any existing encoder-only transformer model without retraining it from scratch. CoSAEmb shows improved performance on information retrieval from the paper{'}s full text in comparison to models trained only on paper titles and abstracts. We also evaluate CoSAEmb on SciRepEval and CSFCube benchmarks, showing comparable performance with existing state-of-the-art models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-singh-2024-cosaemb">
<titleInfo>
<title>CoSAEmb: Contrastive Section-aware Aspect Embeddings for Scientific Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="family">Singh</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>Research papers are long documents that contain information about various aspects such as background, prior work, methodology, and results. Existing works on scientific document representation learning only leverage the title and abstract of the paper. We present CoSAEmb, a model that learns representations from the full text of 97402 scientific papers from the S2ORC dataset. We present a novel supervised contrastive training framework for long documents using triplet loss and margin gradation. Our framework can be used to learn representations of long documents with any existing encoder-only transformer model without retraining it from scratch. CoSAEmb shows improved performance on information retrieval from the paper’s full text in comparison to models trained only on paper titles and abstracts. We also evaluate CoSAEmb on SciRepEval and CSFCube benchmarks, showing comparable performance with existing state-of-the-art models.</abstract>
<identifier type="citekey">singh-singh-2024-cosaemb</identifier>
<location>
<url>https://aclanthology.org/2024.sdp-1.27</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>283</start>
<end>292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoSAEmb: Contrastive Section-aware Aspect Embeddings for Scientific Articles
%A Singh, Shruti
%A Singh, Mayank
%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 singh-singh-2024-cosaemb
%X Research papers are long documents that contain information about various aspects such as background, prior work, methodology, and results. Existing works on scientific document representation learning only leverage the title and abstract of the paper. We present CoSAEmb, a model that learns representations from the full text of 97402 scientific papers from the S2ORC dataset. We present a novel supervised contrastive training framework for long documents using triplet loss and margin gradation. Our framework can be used to learn representations of long documents with any existing encoder-only transformer model without retraining it from scratch. CoSAEmb shows improved performance on information retrieval from the paper’s full text in comparison to models trained only on paper titles and abstracts. We also evaluate CoSAEmb on SciRepEval and CSFCube benchmarks, showing comparable performance with existing state-of-the-art models.
%U https://aclanthology.org/2024.sdp-1.27
%P 283-292
Markdown (Informal)
[CoSAEmb: Contrastive Section-aware Aspect Embeddings for Scientific Articles](https://aclanthology.org/2024.sdp-1.27) (Singh & Singh, sdp-WS 2024)
ACL