@inproceedings{xu-etal-2021-agggen,
title = "{A}gg{G}en: Ordering and Aggregating while Generating",
author = "Xu, Xinnuo and
Du{\v{s}}ek, Ond{\v{r}}ej and
Rieser, Verena and
Konstas, Ioannis",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.113",
doi = "10.18653/v1/2021.acl-long.113",
pages = "1419--1434",
abstract = "We present AggGen (pronounced {`}again{'}) a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-agggen">
<titleInfo>
<title>AggGen: Ordering and Aggregating while Generating</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinnuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Verena</namePart>
<namePart type="family">Rieser</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>
<originInfo>
<dateIssued>2021-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present AggGen (pronounced ‘again’) a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.</abstract>
<identifier type="citekey">xu-etal-2021-agggen</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.113</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.113</url>
</location>
<part>
<date>2021-aug</date>
<extent unit="page">
<start>1419</start>
<end>1434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AggGen: Ordering and Aggregating while Generating
%A Xu, Xinnuo
%A Dušek, Ondřej
%A Rieser, Verena
%A Konstas, Ioannis
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F xu-etal-2021-agggen
%X We present AggGen (pronounced ‘again’) a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.
%R 10.18653/v1/2021.acl-long.113
%U https://aclanthology.org/2021.acl-long.113
%U https://doi.org/10.18653/v1/2021.acl-long.113
%P 1419-1434
Markdown (Informal)
[AggGen: Ordering and Aggregating while Generating](https://aclanthology.org/2021.acl-long.113) (Xu et al., ACL 2021)
ACL
- Xinnuo Xu, Ondřej Dušek, Verena Rieser, and Ioannis Konstas. 2021. AggGen: Ordering and Aggregating while Generating. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1419–1434, Online. Association for Computational Linguistics.