@inproceedings{asaadi-etal-2019-big,
title = "Big {B}i{RD}: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition",
author = "Asaadi, Shima and
Mohammad, Saif and
Kiritchenko, Svetlana",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1050",
doi = "10.18653/v1/N19-1050",
pages = "505--516",
abstract = "Bigrams (two-word sequences) hold a special place in semantic composition research since they are the smallest unit formed by composing words. A semantic relatedness dataset that includes bigrams will thus be useful in the development of automatic methods of semantic composition. However, existing relatedness datasets only include pairs of unigrams (single words). Further, existing datasets were created using rating scales and thus suffer from limitations such as in consistent annotations and scale region bias. In this paper, we describe how we created a large, fine-grained, bigram relatedness dataset (BiRD), using a comparative annotation technique called Best{--}Worst Scaling. Each of BiRD{'}s 3,345 English term pairs involves at least one bigram. We show that the relatedness scores obtained are highly reliable (split-half reliability r= 0.937). We analyze the data to obtain insights into bigram semantic relatedness. Finally, we present benchmark experiments on using the relatedness dataset as a testbed to evaluate simple unsupervised measures of semantic composition. BiRD is made freely available to foster further research on how meaning can be represented and how meaning can be composed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asaadi-etal-2019-big">
<titleInfo>
<title>Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shima</namePart>
<namePart type="family">Asaadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Kiritchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bigrams (two-word sequences) hold a special place in semantic composition research since they are the smallest unit formed by composing words. A semantic relatedness dataset that includes bigrams will thus be useful in the development of automatic methods of semantic composition. However, existing relatedness datasets only include pairs of unigrams (single words). Further, existing datasets were created using rating scales and thus suffer from limitations such as in consistent annotations and scale region bias. In this paper, we describe how we created a large, fine-grained, bigram relatedness dataset (BiRD), using a comparative annotation technique called Best–Worst Scaling. Each of BiRD’s 3,345 English term pairs involves at least one bigram. We show that the relatedness scores obtained are highly reliable (split-half reliability r= 0.937). We analyze the data to obtain insights into bigram semantic relatedness. Finally, we present benchmark experiments on using the relatedness dataset as a testbed to evaluate simple unsupervised measures of semantic composition. BiRD is made freely available to foster further research on how meaning can be represented and how meaning can be composed.</abstract>
<identifier type="citekey">asaadi-etal-2019-big</identifier>
<identifier type="doi">10.18653/v1/N19-1050</identifier>
<location>
<url>https://aclanthology.org/N19-1050</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>505</start>
<end>516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition
%A Asaadi, Shima
%A Mohammad, Saif
%A Kiritchenko, Svetlana
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F asaadi-etal-2019-big
%X Bigrams (two-word sequences) hold a special place in semantic composition research since they are the smallest unit formed by composing words. A semantic relatedness dataset that includes bigrams will thus be useful in the development of automatic methods of semantic composition. However, existing relatedness datasets only include pairs of unigrams (single words). Further, existing datasets were created using rating scales and thus suffer from limitations such as in consistent annotations and scale region bias. In this paper, we describe how we created a large, fine-grained, bigram relatedness dataset (BiRD), using a comparative annotation technique called Best–Worst Scaling. Each of BiRD’s 3,345 English term pairs involves at least one bigram. We show that the relatedness scores obtained are highly reliable (split-half reliability r= 0.937). We analyze the data to obtain insights into bigram semantic relatedness. Finally, we present benchmark experiments on using the relatedness dataset as a testbed to evaluate simple unsupervised measures of semantic composition. BiRD is made freely available to foster further research on how meaning can be represented and how meaning can be composed.
%R 10.18653/v1/N19-1050
%U https://aclanthology.org/N19-1050
%U https://doi.org/10.18653/v1/N19-1050
%P 505-516
Markdown (Informal)
[Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition](https://aclanthology.org/N19-1050) (Asaadi et al., NAACL 2019)
ACL