@inproceedings{qi-etal-2022-takg,
title = "{T}a{KG}: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs",
author = "Qi, Qianqian and
Deng, Zhenyun and
Zhu, Yonghua and
Lee, Lia Jisoo and
Witbrock, Michael and
Liu, Jiamou",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.17",
pages = "176--187",
abstract = "We introduce TaKG, a new table-to-text generation dataset with the following highlights: (1) TaKG defines a long-text (paragraph-level) generation task as opposed to well-established short-text (sentence-level) generation datasets. (2) TaKG is the first large-scale dataset for this task, containing three application domains and {\textasciitilde}750,000 samples. (3) To address the divergence phenomenon, TaKG enhances table input using external knowledge graphs, extracted by a new Wikidata-based method. We then propose a new Transformer-based multimodal sequence-to-sequence architecture for TaKG that integrates two pretrained language models RoBERTa and GPT-2. Our model shows reliable performance on long-text generation across a variety of metrics, and outperforms existing models for short-text generation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2022-takg">
<titleInfo>
<title>TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenyun</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonghua</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lia</namePart>
<namePart type="given">Jisoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Witbrock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiamou</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<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">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</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>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce TaKG, a new table-to-text generation dataset with the following highlights: (1) TaKG defines a long-text (paragraph-level) generation task as opposed to well-established short-text (sentence-level) generation datasets. (2) TaKG is the first large-scale dataset for this task, containing three application domains and ~750,000 samples. (3) To address the divergence phenomenon, TaKG enhances table input using external knowledge graphs, extracted by a new Wikidata-based method. We then propose a new Transformer-based multimodal sequence-to-sequence architecture for TaKG that integrates two pretrained language models RoBERTa and GPT-2. Our model shows reliable performance on long-text generation across a variety of metrics, and outperforms existing models for short-text generation tasks.</abstract>
<identifier type="citekey">qi-etal-2022-takg</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.17</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>176</start>
<end>187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs
%A Qi, Qianqian
%A Deng, Zhenyun
%A Zhu, Yonghua
%A Lee, Lia Jisoo
%A Witbrock, Michael
%A Liu, Jiamou
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F qi-etal-2022-takg
%X We introduce TaKG, a new table-to-text generation dataset with the following highlights: (1) TaKG defines a long-text (paragraph-level) generation task as opposed to well-established short-text (sentence-level) generation datasets. (2) TaKG is the first large-scale dataset for this task, containing three application domains and ~750,000 samples. (3) To address the divergence phenomenon, TaKG enhances table input using external knowledge graphs, extracted by a new Wikidata-based method. We then propose a new Transformer-based multimodal sequence-to-sequence architecture for TaKG that integrates two pretrained language models RoBERTa and GPT-2. Our model shows reliable performance on long-text generation across a variety of metrics, and outperforms existing models for short-text generation tasks.
%U https://aclanthology.org/2022.findings-aacl.17
%P 176-187
Markdown (Informal)
[TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs](https://aclanthology.org/2022.findings-aacl.17) (Qi et al., Findings 2022)
ACL