@inproceedings{dusek-etal-2019-automatic,
title = "Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)",
author = "Du{\v{s}}ek, Ond{\v{r}}ej and
Sevegnani, Karin and
Konstas, Ioannis and
Rieser, Verena",
editor = "van Deemter, Kees and
Lin, Chenghua and
Takamura, Hiroya",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8644",
doi = "10.18653/v1/W19-8644",
pages = "369--376",
abstract = "We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: We synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12{\%} increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dusek et al., 2019), where synthetic data lead to a 4{\%} accuracy increase over the base model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dusek-etal-2019-automatic">
<titleInfo>
<title>Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Sevegnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Rieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-oct–nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">van Deemter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: We synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dusek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.</abstract>
<identifier type="citekey">dusek-etal-2019-automatic</identifier>
<identifier type="doi">10.18653/v1/W19-8644</identifier>
<location>
<url>https://aclanthology.org/W19-8644</url>
</location>
<part>
<date>2019-oct–nov</date>
<extent unit="page">
<start>369</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)
%A Dušek, Ondřej
%A Sevegnani, Karin
%A Konstas, Ioannis
%A Rieser, Verena
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F dusek-etal-2019-automatic
%X We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: We synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dusek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.
%R 10.18653/v1/W19-8644
%U https://aclanthology.org/W19-8644
%U https://doi.org/10.18653/v1/W19-8644
%P 369-376
Markdown (Informal)
[Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)](https://aclanthology.org/W19-8644) (Dušek et al., INLG 2019)
ACL