@inproceedings{cano-bojar-2020-two,
title = "Two Huge Title and Keyword Generation Corpora of Research Articles",
author = "{\c{C}}ano, Erion and
Bojar, Ond{\v{r}}ej",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.823",
pages = "6663--6671",
abstract = "Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and document keywords, stipulating the need for even bigger training corpora. Metadata of research articles are usually easy to find online and can be used to perform research on various tasks. In this paper, we introduce two huge datasets for text summarization (OAGSX) and keyword generation (OAGKX) research, containing 34 million and 23 million records, respectively. The data were retrieved from the Open Academic Graph which is a network of research profiles and publications. We carefully processed each record and also tried several extractive and abstractive methods of both tasks to create performance baselines for other researchers. We further illustrate the performance of those methods previewing their outputs. In the near future, we would like to apply topic modeling on the two sets to derive subsets of research articles from more specific disciplines.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cano-bojar-2020-two">
<titleInfo>
<title>Two Huge Title and Keyword Generation Corpora of Research Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erion</namePart>
<namePart type="family">Çano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and document keywords, stipulating the need for even bigger training corpora. Metadata of research articles are usually easy to find online and can be used to perform research on various tasks. In this paper, we introduce two huge datasets for text summarization (OAGSX) and keyword generation (OAGKX) research, containing 34 million and 23 million records, respectively. The data were retrieved from the Open Academic Graph which is a network of research profiles and publications. We carefully processed each record and also tried several extractive and abstractive methods of both tasks to create performance baselines for other researchers. We further illustrate the performance of those methods previewing their outputs. In the near future, we would like to apply topic modeling on the two sets to derive subsets of research articles from more specific disciplines.</abstract>
<identifier type="citekey">cano-bojar-2020-two</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.823</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>6663</start>
<end>6671</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Two Huge Title and Keyword Generation Corpora of Research Articles
%A Çano, Erion
%A Bojar, Ondřej
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F cano-bojar-2020-two
%X Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and document keywords, stipulating the need for even bigger training corpora. Metadata of research articles are usually easy to find online and can be used to perform research on various tasks. In this paper, we introduce two huge datasets for text summarization (OAGSX) and keyword generation (OAGKX) research, containing 34 million and 23 million records, respectively. The data were retrieved from the Open Academic Graph which is a network of research profiles and publications. We carefully processed each record and also tried several extractive and abstractive methods of both tasks to create performance baselines for other researchers. We further illustrate the performance of those methods previewing their outputs. In the near future, we would like to apply topic modeling on the two sets to derive subsets of research articles from more specific disciplines.
%U https://aclanthology.org/2020.lrec-1.823
%P 6663-6671
Markdown (Informal)
[Two Huge Title and Keyword Generation Corpora of Research Articles](https://aclanthology.org/2020.lrec-1.823) (Çano & Bojar, LREC 2020)
ACL