@inproceedings{ostendorff-etal-2020-aspect,
title = "Aspect-based Document Similarity for Research Papers",
author = "Ostendorff, Malte and
Ruas, Terry and
Blume, Till and
Gipp, Bela and
Rehm, Georg",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.545/",
doi = "10.18653/v1/2020.coling-main.545",
pages = "6194--6206",
abstract = "Traditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents. Typically, they do not consider in what aspects two documents are similar. This limits the granularity of applications like recommender systems that rely on document similarity. In this paper, we extend similarity with aspect information by performing a pairwise document classification task. We evaluate our aspect-based document similarity approach for research papers. Paper citations indicate the aspect-based similarity, i.e., the title of a section in which a citation occurs acts as a label for the pair of citing and cited paper. We apply a series of Transformer models such as RoBERTa, ELECTRA, XLNet, and BERT variations and compare them to an LSTM baseline. We perform our experiments on two newly constructed datasets of 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus. According to our results, SciBERT is the best performing system with F1-scores of up to 0.83. A qualitative analysis validates our quantitative results and indicates that aspect-based document similarity indeed leads to more fine-grained recommendations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ostendorff-etal-2020-aspect">
<titleInfo>
<title>Aspect-based Document Similarity for Research Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Ostendorff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Ruas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Till</namePart>
<namePart type="family">Blume</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Gipp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Traditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents. Typically, they do not consider in what aspects two documents are similar. This limits the granularity of applications like recommender systems that rely on document similarity. In this paper, we extend similarity with aspect information by performing a pairwise document classification task. We evaluate our aspect-based document similarity approach for research papers. Paper citations indicate the aspect-based similarity, i.e., the title of a section in which a citation occurs acts as a label for the pair of citing and cited paper. We apply a series of Transformer models such as RoBERTa, ELECTRA, XLNet, and BERT variations and compare them to an LSTM baseline. We perform our experiments on two newly constructed datasets of 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus. According to our results, SciBERT is the best performing system with F1-scores of up to 0.83. A qualitative analysis validates our quantitative results and indicates that aspect-based document similarity indeed leads to more fine-grained recommendations.</abstract>
<identifier type="citekey">ostendorff-etal-2020-aspect</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.545</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.545/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>6194</start>
<end>6206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aspect-based Document Similarity for Research Papers
%A Ostendorff, Malte
%A Ruas, Terry
%A Blume, Till
%A Gipp, Bela
%A Rehm, Georg
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F ostendorff-etal-2020-aspect
%X Traditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents. Typically, they do not consider in what aspects two documents are similar. This limits the granularity of applications like recommender systems that rely on document similarity. In this paper, we extend similarity with aspect information by performing a pairwise document classification task. We evaluate our aspect-based document similarity approach for research papers. Paper citations indicate the aspect-based similarity, i.e., the title of a section in which a citation occurs acts as a label for the pair of citing and cited paper. We apply a series of Transformer models such as RoBERTa, ELECTRA, XLNet, and BERT variations and compare them to an LSTM baseline. We perform our experiments on two newly constructed datasets of 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus. According to our results, SciBERT is the best performing system with F1-scores of up to 0.83. A qualitative analysis validates our quantitative results and indicates that aspect-based document similarity indeed leads to more fine-grained recommendations.
%R 10.18653/v1/2020.coling-main.545
%U https://aclanthology.org/2020.coling-main.545/
%U https://doi.org/10.18653/v1/2020.coling-main.545
%P 6194-6206
Markdown (Informal)
[Aspect-based Document Similarity for Research Papers](https://aclanthology.org/2020.coling-main.545/) (Ostendorff et al., COLING 2020)
ACL
- Malte Ostendorff, Terry Ruas, Till Blume, Bela Gipp, and Georg Rehm. 2020. Aspect-based Document Similarity for Research Papers. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6194–6206, Barcelona, Spain (Online). International Committee on Computational Linguistics.