@inproceedings{wang-etal-2021-wikigraphs,
title = "{W}iki{G}raphs: A {W}ikipedia Text - Knowledge Graph Paired Dataset",
author = "Wang, Luyu and
Li, Yujia and
Aslan, Ozlem and
Vinyals, Oriol",
editor = "Panchenko, Alexander and
Malliaros, Fragkiskos D. and
Logacheva, Varvara and
Jana, Abhik and
Ustalov, Dmitry and
Jansen, Peter",
booktitle = "Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)",
month = jun,
year = "2021",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.textgraphs-1.7",
doi = "10.18653/v1/2021.textgraphs-1.7",
pages = "67--82",
abstract = "We present a new dataset of Wikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning. Existing graph-text paired datasets typically contain small graphs and short text (1 or few sentences), thus limiting the capabilities of the models that can be learned on the data. Our new dataset WikiGraphs is collected by pairing each Wikipedia article from the established WikiText-103 benchmark (Merity et al., 2016) with a subgraph from the Freebase knowledge graph (Bollacker et al., 2008). This makes it easy to benchmark against other state-of-the-art text generative models that are capable of generating long paragraphs of coherent text. Both the graphs and the text data are of significantly larger scale compared to prior graph-text paired datasets. We present baseline graph neural network and transformer model results on our dataset for 3 tasks: graph -{\textgreater} text generation, graph -{\textgreater} text retrieval and text -{\textgreater} graph retrieval. We show that better conditioning on the graph provides gains in generation and retrieval quality but there is still large room for improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-wikigraphs">
<titleInfo>
<title>WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujia</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozlem</namePart>
<namePart type="family">Aslan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oriol</namePart>
<namePart type="family">Vinyals</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fragkiskos</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Malliaros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ustalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new dataset of Wikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning. Existing graph-text paired datasets typically contain small graphs and short text (1 or few sentences), thus limiting the capabilities of the models that can be learned on the data. Our new dataset WikiGraphs is collected by pairing each Wikipedia article from the established WikiText-103 benchmark (Merity et al., 2016) with a subgraph from the Freebase knowledge graph (Bollacker et al., 2008). This makes it easy to benchmark against other state-of-the-art text generative models that are capable of generating long paragraphs of coherent text. Both the graphs and the text data are of significantly larger scale compared to prior graph-text paired datasets. We present baseline graph neural network and transformer model results on our dataset for 3 tasks: graph -\textgreater text generation, graph -\textgreater text retrieval and text -\textgreater graph retrieval. We show that better conditioning on the graph provides gains in generation and retrieval quality but there is still large room for improvement.</abstract>
<identifier type="citekey">wang-etal-2021-wikigraphs</identifier>
<identifier type="doi">10.18653/v1/2021.textgraphs-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.textgraphs-1.7</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>67</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
%A Wang, Luyu
%A Li, Yujia
%A Aslan, Ozlem
%A Vinyals, Oriol
%Y Panchenko, Alexander
%Y Malliaros, Fragkiskos D.
%Y Logacheva, Varvara
%Y Jana, Abhik
%Y Ustalov, Dmitry
%Y Jansen, Peter
%S Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
%D 2021
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wang-etal-2021-wikigraphs
%X We present a new dataset of Wikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning. Existing graph-text paired datasets typically contain small graphs and short text (1 or few sentences), thus limiting the capabilities of the models that can be learned on the data. Our new dataset WikiGraphs is collected by pairing each Wikipedia article from the established WikiText-103 benchmark (Merity et al., 2016) with a subgraph from the Freebase knowledge graph (Bollacker et al., 2008). This makes it easy to benchmark against other state-of-the-art text generative models that are capable of generating long paragraphs of coherent text. Both the graphs and the text data are of significantly larger scale compared to prior graph-text paired datasets. We present baseline graph neural network and transformer model results on our dataset for 3 tasks: graph -\textgreater text generation, graph -\textgreater text retrieval and text -\textgreater graph retrieval. We show that better conditioning on the graph provides gains in generation and retrieval quality but there is still large room for improvement.
%R 10.18653/v1/2021.textgraphs-1.7
%U https://aclanthology.org/2021.textgraphs-1.7
%U https://doi.org/10.18653/v1/2021.textgraphs-1.7
%P 67-82
Markdown (Informal)
[WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset](https://aclanthology.org/2021.textgraphs-1.7) (Wang et al., TextGraphs 2021)
ACL
- Luyu Wang, Yujia Li, Ozlem Aslan, and Oriol Vinyals. 2021. WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset. In Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), pages 67–82, Mexico City, Mexico. Association for Computational Linguistics.