@inproceedings{skrjanec-etal-2022-barch,
title = "Barch: an {E}nglish Dataset of Bar Chart Summaries",
author = "{\v{S}}krjanec, Iza and
Edhi, Muhammad Salman and
Demberg, Vera",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.380",
pages = "3552--3560",
abstract = "We present Barch, a new English dataset of human-written summaries describing bar charts. This dataset contains 47 charts based on a selection of 18 topics. Each chart is associated with one of the four intended messages expressed in the chart title. Using crowdsourcing, we collected around 20 summaries per chart, or one thousand in total. The text of the summaries is aligned with the chart data as well as with analytical inferences about the data drawn by humans. Our datasets is one of the first to explore the effect of intended messages on the data descriptions in chart summaries. Additionally, it lends itself well to the task of training data-driven systems for chart-to-text generation. We provide results on the performance of state-of-the-art neural generation models trained on this dataset and discuss the strengths and shortcomings of different models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skrjanec-etal-2022-barch">
<titleInfo>
<title>Barch: an English Dataset of Bar Chart Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iza</namePart>
<namePart type="family">Škrjanec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Salman</namePart>
<namePart type="family">Edhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Barch, a new English dataset of human-written summaries describing bar charts. This dataset contains 47 charts based on a selection of 18 topics. Each chart is associated with one of the four intended messages expressed in the chart title. Using crowdsourcing, we collected around 20 summaries per chart, or one thousand in total. The text of the summaries is aligned with the chart data as well as with analytical inferences about the data drawn by humans. Our datasets is one of the first to explore the effect of intended messages on the data descriptions in chart summaries. Additionally, it lends itself well to the task of training data-driven systems for chart-to-text generation. We provide results on the performance of state-of-the-art neural generation models trained on this dataset and discuss the strengths and shortcomings of different models.</abstract>
<identifier type="citekey">skrjanec-etal-2022-barch</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.380</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3552</start>
<end>3560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Barch: an English Dataset of Bar Chart Summaries
%A Škrjanec, Iza
%A Edhi, Muhammad Salman
%A Demberg, Vera
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F skrjanec-etal-2022-barch
%X We present Barch, a new English dataset of human-written summaries describing bar charts. This dataset contains 47 charts based on a selection of 18 topics. Each chart is associated with one of the four intended messages expressed in the chart title. Using crowdsourcing, we collected around 20 summaries per chart, or one thousand in total. The text of the summaries is aligned with the chart data as well as with analytical inferences about the data drawn by humans. Our datasets is one of the first to explore the effect of intended messages on the data descriptions in chart summaries. Additionally, it lends itself well to the task of training data-driven systems for chart-to-text generation. We provide results on the performance of state-of-the-art neural generation models trained on this dataset and discuss the strengths and shortcomings of different models.
%U https://aclanthology.org/2022.lrec-1.380
%P 3552-3560
Markdown (Informal)
[Barch: an English Dataset of Bar Chart Summaries](https://aclanthology.org/2022.lrec-1.380) (Škrjanec et al., LREC 2022)
ACL
- Iza Škrjanec, Muhammad Salman Edhi, and Vera Demberg. 2022. Barch: an English Dataset of Bar Chart Summaries. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3552–3560, Marseille, France. European Language Resources Association.