@inproceedings{du-black-2019-learning,
title = "Learning to Order Graph Elements with Application to Multilingual Surface Realization",
author = "Du, Wenchao and
Black, Alan W",
editor = "Mille, Simon and
Belz, Anja and
Bohnet, Bernd and
Graham, Yvette and
Wanner, Leo",
booktitle = "Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6302",
doi = "10.18653/v1/D19-6302",
pages = "18--24",
abstract = "Recent advances in deep learning have shown promises in solving complex combinatorial optimization problems, such as sorting variable-sized sequences. In this work, we take a step further and tackle the problem of ordering the elements of sequences that come with graph structures. Our solution adopts an encoder-decoder framework, in which the encoder is a graph neural network that learns the representation for each element, and the decoder predicts the ordering of each local neighborhood of the graph in turn. We apply our framework to multilingual surface realization, which is the task of ordering and completing sentences with their dependency parses given but without the ordering of words. Experiments show that our approach is much better for this task than prior works that do not consider graph structures. We participated in 2019 Surface Realization Shared Task (SR{'}19), and we ranked second out of 14 teams while outperforming those teams below by a large margin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-black-2019-learning">
<titleInfo>
<title>Learning to Order Graph Elements with Application to Multilingual Surface Realization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenchao</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anja</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernd</namePart>
<namePart type="family">Bohnet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in deep learning have shown promises in solving complex combinatorial optimization problems, such as sorting variable-sized sequences. In this work, we take a step further and tackle the problem of ordering the elements of sequences that come with graph structures. Our solution adopts an encoder-decoder framework, in which the encoder is a graph neural network that learns the representation for each element, and the decoder predicts the ordering of each local neighborhood of the graph in turn. We apply our framework to multilingual surface realization, which is the task of ordering and completing sentences with their dependency parses given but without the ordering of words. Experiments show that our approach is much better for this task than prior works that do not consider graph structures. We participated in 2019 Surface Realization Shared Task (SR’19), and we ranked second out of 14 teams while outperforming those teams below by a large margin.</abstract>
<identifier type="citekey">du-black-2019-learning</identifier>
<identifier type="doi">10.18653/v1/D19-6302</identifier>
<location>
<url>https://aclanthology.org/D19-6302</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>18</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Order Graph Elements with Application to Multilingual Surface Realization
%A Du, Wenchao
%A Black, Alan W.
%Y Mille, Simon
%Y Belz, Anja
%Y Bohnet, Bernd
%Y Graham, Yvette
%Y Wanner, Leo
%S Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F du-black-2019-learning
%X Recent advances in deep learning have shown promises in solving complex combinatorial optimization problems, such as sorting variable-sized sequences. In this work, we take a step further and tackle the problem of ordering the elements of sequences that come with graph structures. Our solution adopts an encoder-decoder framework, in which the encoder is a graph neural network that learns the representation for each element, and the decoder predicts the ordering of each local neighborhood of the graph in turn. We apply our framework to multilingual surface realization, which is the task of ordering and completing sentences with their dependency parses given but without the ordering of words. Experiments show that our approach is much better for this task than prior works that do not consider graph structures. We participated in 2019 Surface Realization Shared Task (SR’19), and we ranked second out of 14 teams while outperforming those teams below by a large margin.
%R 10.18653/v1/D19-6302
%U https://aclanthology.org/D19-6302
%U https://doi.org/10.18653/v1/D19-6302
%P 18-24
Markdown (Informal)
[Learning to Order Graph Elements with Application to Multilingual Surface Realization](https://aclanthology.org/D19-6302) (Du & Black, 2019)
ACL