@inproceedings{upadhyay-massie-2022-content,
title = "Content Type Profiling of Data-to-Text Generation Datasets",
author = "Upadhyay, Ashish and
Massie, Stewart",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.507",
pages = "5770--5782",
abstract = "Data-to-Text Generation (D2T) problems can be considered as a stream of time-stamped events with a text summary being produced for each. The problem becomes more challenging when event summaries contain complex insights derived from multiple records either within an event, or across several events from the event stream. It is important to understand the different types of content present in the summary to help us better define the system requirements so that we can build better systems. In this paper, we propose a novel typology of content types, that we use to classify the contents of event summaries. Using the typology, a profile of a dataset is generated as the distribution of the aggregated content types which captures the specific characteristics of the dataset and gives a measure of the complexity present in the problem. Extensive experimentation on different D2T datasets is performed and these demonstrate that neural systems struggle in generating contents of complex types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="upadhyay-massie-2022-content">
<titleInfo>
<title>Content Type Profiling of Data-to-Text Generation Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Upadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stewart</namePart>
<namePart type="family">Massie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data-to-Text Generation (D2T) problems can be considered as a stream of time-stamped events with a text summary being produced for each. The problem becomes more challenging when event summaries contain complex insights derived from multiple records either within an event, or across several events from the event stream. It is important to understand the different types of content present in the summary to help us better define the system requirements so that we can build better systems. In this paper, we propose a novel typology of content types, that we use to classify the contents of event summaries. Using the typology, a profile of a dataset is generated as the distribution of the aggregated content types which captures the specific characteristics of the dataset and gives a measure of the complexity present in the problem. Extensive experimentation on different D2T datasets is performed and these demonstrate that neural systems struggle in generating contents of complex types.</abstract>
<identifier type="citekey">upadhyay-massie-2022-content</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.507</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5770</start>
<end>5782</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Content Type Profiling of Data-to-Text Generation Datasets
%A Upadhyay, Ashish
%A Massie, Stewart
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F upadhyay-massie-2022-content
%X Data-to-Text Generation (D2T) problems can be considered as a stream of time-stamped events with a text summary being produced for each. The problem becomes more challenging when event summaries contain complex insights derived from multiple records either within an event, or across several events from the event stream. It is important to understand the different types of content present in the summary to help us better define the system requirements so that we can build better systems. In this paper, we propose a novel typology of content types, that we use to classify the contents of event summaries. Using the typology, a profile of a dataset is generated as the distribution of the aggregated content types which captures the specific characteristics of the dataset and gives a measure of the complexity present in the problem. Extensive experimentation on different D2T datasets is performed and these demonstrate that neural systems struggle in generating contents of complex types.
%U https://aclanthology.org/2022.coling-1.507
%P 5770-5782
Markdown (Informal)
[Content Type Profiling of Data-to-Text Generation Datasets](https://aclanthology.org/2022.coling-1.507) (Upadhyay & Massie, COLING 2022)
ACL