@inproceedings{chang-etal-2021-neural,
title = "Neural Data-to-Text Generation with {LM}-based Text Augmentation",
author = "Chang, Ernie and
Shen, Xiaoyu and
Zhu, Dawei and
Demberg, Vera and
Su, Hui",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.64",
doi = "10.18653/v1/2021.eacl-main.64",
pages = "758--768",
abstract = "For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text samples are available. To address this problem, we here propose a novel few-shot approach for this setting. Our approach automatically augments the data available for training by (i) generating new text samples based on replacing specific values by alternative ones from the same category, (ii) generating new text samples based on GPT-2, and (iii) proposing an automatic method for pairing the new text samples with data samples. As the text augmentation can introduce noise to the training data, we use cycle consistency as an objective, in order to make sure that a given data sample can be correctly reconstructed after having been formulated as text (and that text samples can be reconstructed from data). On both the E2E and WebNLG benchmarks, we show that this weakly supervised training paradigm is able to outperform fully supervised sequence-to-sequence models with less than 10{\%} of the training set. By utilizing all annotated data, our model can boost the performance of a standard sequence-to-sequence model by over 5 BLEU points, establishing a new state-of-the-art on both datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2021-neural">
<titleInfo>
<title>Neural Data-to-Text Generation with LM-based Text Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernie</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text samples are available. To address this problem, we here propose a novel few-shot approach for this setting. Our approach automatically augments the data available for training by (i) generating new text samples based on replacing specific values by alternative ones from the same category, (ii) generating new text samples based on GPT-2, and (iii) proposing an automatic method for pairing the new text samples with data samples. As the text augmentation can introduce noise to the training data, we use cycle consistency as an objective, in order to make sure that a given data sample can be correctly reconstructed after having been formulated as text (and that text samples can be reconstructed from data). On both the E2E and WebNLG benchmarks, we show that this weakly supervised training paradigm is able to outperform fully supervised sequence-to-sequence models with less than 10% of the training set. By utilizing all annotated data, our model can boost the performance of a standard sequence-to-sequence model by over 5 BLEU points, establishing a new state-of-the-art on both datasets.</abstract>
<identifier type="citekey">chang-etal-2021-neural</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.64</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.64</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>758</start>
<end>768</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Data-to-Text Generation with LM-based Text Augmentation
%A Chang, Ernie
%A Shen, Xiaoyu
%A Zhu, Dawei
%A Demberg, Vera
%A Su, Hui
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F chang-etal-2021-neural
%X For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text samples are available. To address this problem, we here propose a novel few-shot approach for this setting. Our approach automatically augments the data available for training by (i) generating new text samples based on replacing specific values by alternative ones from the same category, (ii) generating new text samples based on GPT-2, and (iii) proposing an automatic method for pairing the new text samples with data samples. As the text augmentation can introduce noise to the training data, we use cycle consistency as an objective, in order to make sure that a given data sample can be correctly reconstructed after having been formulated as text (and that text samples can be reconstructed from data). On both the E2E and WebNLG benchmarks, we show that this weakly supervised training paradigm is able to outperform fully supervised sequence-to-sequence models with less than 10% of the training set. By utilizing all annotated data, our model can boost the performance of a standard sequence-to-sequence model by over 5 BLEU points, establishing a new state-of-the-art on both datasets.
%R 10.18653/v1/2021.eacl-main.64
%U https://aclanthology.org/2021.eacl-main.64
%U https://doi.org/10.18653/v1/2021.eacl-main.64
%P 758-768
Markdown (Informal)
[Neural Data-to-Text Generation with LM-based Text Augmentation](https://aclanthology.org/2021.eacl-main.64) (Chang et al., EACL 2021)
ACL
- Ernie Chang, Xiaoyu Shen, Dawei Zhu, Vera Demberg, and Hui Su. 2021. Neural Data-to-Text Generation with LM-based Text Augmentation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 758–768, Online. Association for Computational Linguistics.