@inproceedings{omura-etal-2020-method,
title = "A Method for Building a Commonsense Inference Dataset based on Basic Events",
author = "Omura, Kazumasa and
Kawahara, Daisuke and
Kurohashi, Sadao",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.192",
doi = "10.18653/v1/2020.emnlp-main.192",
pages = "2450--2460",
abstract = "We present a scalable, low-bias, and low-cost method for building a commonsense inference dataset that combines automatic extraction from a corpus and crowdsourcing. Each problem is a multiple-choice question that asks contingency between basic events. We applied the proposed method to a Japanese corpus and acquired 104k problems. While humans can solve the resulting problems with high accuracy (88.9{\%}), the accuracy of a high-performance transfer learning model is reasonably low (76.0{\%}). We also confirmed through dataset analysis that the resulting dataset contains low bias. We released the datatset to facilitate language understanding research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="omura-etal-2020-method">
<titleInfo>
<title>A Method for Building a Commonsense Inference Dataset based on Basic Events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazumasa</namePart>
<namePart type="family">Omura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a scalable, low-bias, and low-cost method for building a commonsense inference dataset that combines automatic extraction from a corpus and crowdsourcing. Each problem is a multiple-choice question that asks contingency between basic events. We applied the proposed method to a Japanese corpus and acquired 104k problems. While humans can solve the resulting problems with high accuracy (88.9%), the accuracy of a high-performance transfer learning model is reasonably low (76.0%). We also confirmed through dataset analysis that the resulting dataset contains low bias. We released the datatset to facilitate language understanding research.</abstract>
<identifier type="citekey">omura-etal-2020-method</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.192</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.192</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2450</start>
<end>2460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Method for Building a Commonsense Inference Dataset based on Basic Events
%A Omura, Kazumasa
%A Kawahara, Daisuke
%A Kurohashi, Sadao
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F omura-etal-2020-method
%X We present a scalable, low-bias, and low-cost method for building a commonsense inference dataset that combines automatic extraction from a corpus and crowdsourcing. Each problem is a multiple-choice question that asks contingency between basic events. We applied the proposed method to a Japanese corpus and acquired 104k problems. While humans can solve the resulting problems with high accuracy (88.9%), the accuracy of a high-performance transfer learning model is reasonably low (76.0%). We also confirmed through dataset analysis that the resulting dataset contains low bias. We released the datatset to facilitate language understanding research.
%R 10.18653/v1/2020.emnlp-main.192
%U https://aclanthology.org/2020.emnlp-main.192
%U https://doi.org/10.18653/v1/2020.emnlp-main.192
%P 2450-2460
Markdown (Informal)
[A Method for Building a Commonsense Inference Dataset based on Basic Events](https://aclanthology.org/2020.emnlp-main.192) (Omura et al., EMNLP 2020)
ACL