@inproceedings{leng-etal-2020-controllable,
title = "Controllable Neural Natural Language Generation: comparison of state-of-the-art control strategies",
author = "Leng, Yuanmin and
Portet, Fran{\c{c}}ois and
Labb{\'e}, Cyril and
Qader, Raheel",
editor = "Castro Ferreira, Thiago and
Gardent, Claire and
Ilinykh, Nikolai and
van der Lee, Chris and
Mille, Simon and
Moussallem, Diego and
Shimorina, Anastasia",
booktitle = "Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)",
month = "12",
year = "2020",
address = "Dublin, Ireland (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.webnlg-1.4",
pages = "34--39",
abstract = "Most NLG systems target text fluency and grammatical correctness, disregarding control over text structure and length. However, control over the output plays an important part in industrial NLG applications. In this paper, we study different strategies of control in triple-totext generation systems particularly from the aspects of text structure and text length. Regarding text structure, we present an approach that relies on aligning the input entities with the facts in the target side. It makes sure that the order and the distribution of entities in both the input and the text are the same. As for control over text length, we show two different approaches. One is to supply length constraint as input while the other is to force the end-ofsentence tag to be included at each step when using top-k decoding strategy. Finally, we propose four metrics to assess the degree to which these methods will affect a NLG system{'}s ability to control text structure and length. Our analyses demonstrate that all the methods enhance the system{'}s ability with a slight decrease in text fluency. In addition, constraining length at the input level performs much better than control at decoding level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leng-etal-2020-controllable">
<titleInfo>
<title>Controllable Neural Natural Language Generation: comparison of state-of-the-art control strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanmin</namePart>
<namePart type="family">Leng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Portet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Labbé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raheel</namePart>
<namePart type="family">Qader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="family">Castro Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Gardent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">van der Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Diego</namePart>
<namePart type="family">Moussallem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most NLG systems target text fluency and grammatical correctness, disregarding control over text structure and length. However, control over the output plays an important part in industrial NLG applications. In this paper, we study different strategies of control in triple-totext generation systems particularly from the aspects of text structure and text length. Regarding text structure, we present an approach that relies on aligning the input entities with the facts in the target side. It makes sure that the order and the distribution of entities in both the input and the text are the same. As for control over text length, we show two different approaches. One is to supply length constraint as input while the other is to force the end-ofsentence tag to be included at each step when using top-k decoding strategy. Finally, we propose four metrics to assess the degree to which these methods will affect a NLG system’s ability to control text structure and length. Our analyses demonstrate that all the methods enhance the system’s ability with a slight decrease in text fluency. In addition, constraining length at the input level performs much better than control at decoding level.</abstract>
<identifier type="citekey">leng-etal-2020-controllable</identifier>
<location>
<url>https://aclanthology.org/2020.webnlg-1.4</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>34</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controllable Neural Natural Language Generation: comparison of state-of-the-art control strategies
%A Leng, Yuanmin
%A Portet, François
%A Labbé, Cyril
%A Qader, Raheel
%Y Castro Ferreira, Thiago
%Y Gardent, Claire
%Y Ilinykh, Nikolai
%Y van der Lee, Chris
%Y Mille, Simon
%Y Moussallem, Diego
%Y Shimorina, Anastasia
%S Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)
%D 2020
%8 December
%I Association for Computational Linguistics
%C Dublin, Ireland (Virtual)
%F leng-etal-2020-controllable
%X Most NLG systems target text fluency and grammatical correctness, disregarding control over text structure and length. However, control over the output plays an important part in industrial NLG applications. In this paper, we study different strategies of control in triple-totext generation systems particularly from the aspects of text structure and text length. Regarding text structure, we present an approach that relies on aligning the input entities with the facts in the target side. It makes sure that the order and the distribution of entities in both the input and the text are the same. As for control over text length, we show two different approaches. One is to supply length constraint as input while the other is to force the end-ofsentence tag to be included at each step when using top-k decoding strategy. Finally, we propose four metrics to assess the degree to which these methods will affect a NLG system’s ability to control text structure and length. Our analyses demonstrate that all the methods enhance the system’s ability with a slight decrease in text fluency. In addition, constraining length at the input level performs much better than control at decoding level.
%U https://aclanthology.org/2020.webnlg-1.4
%P 34-39
Markdown (Informal)
[Controllable Neural Natural Language Generation: comparison of state-of-the-art control strategies](https://aclanthology.org/2020.webnlg-1.4) (Leng et al., WebNLG 2020)
ACL