@inproceedings{kale-rastogi-2020-text,
title = "Text-to-Text Pre-Training for Data-to-Text Tasks",
author = "Kale, Mihir and
Rastogi, Abhinav",
editor = "Davis, Brian and
Graham, Yvette and
Kelleher, John and
Sripada, Yaji",
booktitle = "Proceedings of the 13th International Conference on Natural Language Generation",
month = dec,
year = "2020",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.inlg-1.14",
doi = "10.18653/v1/2020.inlg-1.14",
pages = "97--102",
abstract = "We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5 (Raffel et al., 2019), enables simple, end-to-end transformer based models to outperform pipelined neural architectures tailored for data-to-text generation, as well as alternatives such as BERT and GPT-2. Importantly, T5 pre-training leads to better generalization, as evidenced by large improvements on out-ofdomain test sets. We hope our work serves as a useful baseline for future research, as transfer learning becomes ever more prevalent for data-to-text tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kale-rastogi-2020-text">
<titleInfo>
<title>Text-to-Text Pre-Training for Data-to-Text Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihir</namePart>
<namePart type="family">Kale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</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 13th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Davis</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">John</namePart>
<namePart type="family">Kelleher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaji</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5 (Raffel et al., 2019), enables simple, end-to-end transformer based models to outperform pipelined neural architectures tailored for data-to-text generation, as well as alternatives such as BERT and GPT-2. Importantly, T5 pre-training leads to better generalization, as evidenced by large improvements on out-ofdomain test sets. We hope our work serves as a useful baseline for future research, as transfer learning becomes ever more prevalent for data-to-text tasks.</abstract>
<identifier type="citekey">kale-rastogi-2020-text</identifier>
<identifier type="doi">10.18653/v1/2020.inlg-1.14</identifier>
<location>
<url>https://aclanthology.org/2020.inlg-1.14</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>97</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-to-Text Pre-Training for Data-to-Text Tasks
%A Kale, Mihir
%A Rastogi, Abhinav
%Y Davis, Brian
%Y Graham, Yvette
%Y Kelleher, John
%Y Sripada, Yaji
%S Proceedings of the 13th International Conference on Natural Language Generation
%D 2020
%8 December
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kale-rastogi-2020-text
%X We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5 (Raffel et al., 2019), enables simple, end-to-end transformer based models to outperform pipelined neural architectures tailored for data-to-text generation, as well as alternatives such as BERT and GPT-2. Importantly, T5 pre-training leads to better generalization, as evidenced by large improvements on out-ofdomain test sets. We hope our work serves as a useful baseline for future research, as transfer learning becomes ever more prevalent for data-to-text tasks.
%R 10.18653/v1/2020.inlg-1.14
%U https://aclanthology.org/2020.inlg-1.14
%U https://doi.org/10.18653/v1/2020.inlg-1.14
%P 97-102
Markdown (Informal)
[Text-to-Text Pre-Training for Data-to-Text Tasks](https://aclanthology.org/2020.inlg-1.14) (Kale & Rastogi, INLG 2020)
ACL
- Mihir Kale and Abhinav Rastogi. 2020. Text-to-Text Pre-Training for Data-to-Text Tasks. In Proceedings of the 13th International Conference on Natural Language Generation, pages 97–102, Dublin, Ireland. Association for Computational Linguistics.