@inproceedings{li-etal-2020-leveraging,
title = "Leveraging Large Pretrained Models for {W}eb{NLG} 2020",
author = "Li, Xintong and
Maskharashvili, Aleksandre and
Jory Stevens-Guille, Symon and
White, Michael",
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-1.12",
pages = "117--124",
abstract = "In this paper, we report experiments on finetuning large pretrained models to realize resource description framework (RDF) triples to natural language. We provide the details of how to build one of the top-ranked English generation models in WebNLG Challenge 2020. We also show that there appears to be considerable potential for reranking to improve the current state of the art both in terms of statistical metrics and model-based metrics. Our human analyses of the generated texts show that for Russian, pretrained models showed some success, both in terms of lexical and morpho-syntactic choices for generation, as well as for content aggregation. Nevertheless, in a number of cases, the model can be unpredictable, both in terms of failure or success. Omissions of the content and hallucinations, which in many cases occurred at the same time, were major problems. By contrast, the models for English showed near perfect performance on the validation set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-leveraging">
<titleInfo>
<title>Leveraging Large Pretrained Models for WebNLG 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xintong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandre</namePart>
<namePart type="family">Maskharashvili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Symon</namePart>
<namePart type="family">Jory Stevens-Guille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">White</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>In this paper, we report experiments on finetuning large pretrained models to realize resource description framework (RDF) triples to natural language. We provide the details of how to build one of the top-ranked English generation models in WebNLG Challenge 2020. We also show that there appears to be considerable potential for reranking to improve the current state of the art both in terms of statistical metrics and model-based metrics. Our human analyses of the generated texts show that for Russian, pretrained models showed some success, both in terms of lexical and morpho-syntactic choices for generation, as well as for content aggregation. Nevertheless, in a number of cases, the model can be unpredictable, both in terms of failure or success. Omissions of the content and hallucinations, which in many cases occurred at the same time, were major problems. By contrast, the models for English showed near perfect performance on the validation set.</abstract>
<identifier type="citekey">li-etal-2020-leveraging</identifier>
<location>
<url>https://aclanthology.org/2020.webnlg-1.12</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>117</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Large Pretrained Models for WebNLG 2020
%A Li, Xintong
%A Maskharashvili, Aleksandre
%A Jory Stevens-Guille, Symon
%A White, Michael
%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 li-etal-2020-leveraging
%X In this paper, we report experiments on finetuning large pretrained models to realize resource description framework (RDF) triples to natural language. We provide the details of how to build one of the top-ranked English generation models in WebNLG Challenge 2020. We also show that there appears to be considerable potential for reranking to improve the current state of the art both in terms of statistical metrics and model-based metrics. Our human analyses of the generated texts show that for Russian, pretrained models showed some success, both in terms of lexical and morpho-syntactic choices for generation, as well as for content aggregation. Nevertheless, in a number of cases, the model can be unpredictable, both in terms of failure or success. Omissions of the content and hallucinations, which in many cases occurred at the same time, were major problems. By contrast, the models for English showed near perfect performance on the validation set.
%U https://aclanthology.org/2020.webnlg-1.12
%P 117-124
Markdown (Informal)
[Leveraging Large Pretrained Models for WebNLG 2020](https://aclanthology.org/2020.webnlg-1.12) (Li et al., WebNLG 2020)
ACL
- Xintong Li, Aleksandre Maskharashvili, Symon Jory Stevens-Guille, and Michael White. 2020. Leveraging Large Pretrained Models for WebNLG 2020. In Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+), pages 117–124, Dublin, Ireland (Virtual). Association for Computational Linguistics.