@inproceedings{westera-etal-2020-similarity,
title = "Similarity or deeper understanding? Analyzing the {TED}-{Q} dataset of evoked questions",
author = "Westera, Matthijs and
Amidei, Jacopo and
Mayol, Laia",
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.439",
doi = "10.18653/v1/2020.coling-main.439",
pages = "5004--5012",
abstract = "We take a close look at a recent dataset of TED-talks annotated with the questions they implicitly evoke, TED-Q (Westera et al., 2020). We test to what extent the relation between a discourse and the questions it evokes is merely one of similarity or association, as opposed to deeper semantic/pragmatic interpretation. We do so by turning the TED-Q dataset into a binary classification task, constructing an analogous task from explicit questions we extract from the BookCorpus (Zhu et al., 2015), and fitting a BERT-based classifier alongside models based on different notions of similarity. The BERT-based classifier, achieving close to human performance, outperforms all similarity-based models, suggesting that there is more to identifying true evoked questions than plain similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="westera-etal-2020-similarity">
<titleInfo>
<title>Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthijs</namePart>
<namePart type="family">Westera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Amidei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laia</namePart>
<namePart type="family">Mayol</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>We take a close look at a recent dataset of TED-talks annotated with the questions they implicitly evoke, TED-Q (Westera et al., 2020). We test to what extent the relation between a discourse and the questions it evokes is merely one of similarity or association, as opposed to deeper semantic/pragmatic interpretation. We do so by turning the TED-Q dataset into a binary classification task, constructing an analogous task from explicit questions we extract from the BookCorpus (Zhu et al., 2015), and fitting a BERT-based classifier alongside models based on different notions of similarity. The BERT-based classifier, achieving close to human performance, outperforms all similarity-based models, suggesting that there is more to identifying true evoked questions than plain similarity.</abstract>
<identifier type="citekey">westera-etal-2020-similarity</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.439</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.439</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5004</start>
<end>5012</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions
%A Westera, Matthijs
%A Amidei, Jacopo
%A Mayol, Laia
%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 westera-etal-2020-similarity
%X We take a close look at a recent dataset of TED-talks annotated with the questions they implicitly evoke, TED-Q (Westera et al., 2020). We test to what extent the relation between a discourse and the questions it evokes is merely one of similarity or association, as opposed to deeper semantic/pragmatic interpretation. We do so by turning the TED-Q dataset into a binary classification task, constructing an analogous task from explicit questions we extract from the BookCorpus (Zhu et al., 2015), and fitting a BERT-based classifier alongside models based on different notions of similarity. The BERT-based classifier, achieving close to human performance, outperforms all similarity-based models, suggesting that there is more to identifying true evoked questions than plain similarity.
%R 10.18653/v1/2020.coling-main.439
%U https://aclanthology.org/2020.coling-main.439
%U https://doi.org/10.18653/v1/2020.coling-main.439
%P 5004-5012
Markdown (Informal)
[Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions](https://aclanthology.org/2020.coling-main.439) (Westera et al., COLING 2020)
ACL