@inproceedings{nan-etal-2022-r2d2,
title = "{R}2{D}2: Robust Data-to-Text with Replacement Detection",
author = "Nan, Linyong and
Flores, Lorenzo Jaime and
Zhao, Yilun and
Liu, Yixin and
Benson, Luke and
Zou, Weijin and
Radev, Dragomir",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.464",
doi = "10.18653/v1/2022.emnlp-main.464",
pages = "6903--6917",
abstract = "Unfaithful text generation is a common problem for text generation systems. In the case of Data-to-Text (D2T) systems, the factuality of the generated text is particularly crucial for any real-world applications. We introduce R2D2, a training framework that addresses unfaithful Data-to-Text generation by training a system both as a generator and a faithfulness discriminator with additional replacement detection and unlikelihood learning tasks. To facilitate such training, we propose two methods for sampling unfaithful sentences. We argue that the poor entity retrieval capability of D2T systems is one of the primary sources of unfaithfulness, so in addition to the existing metrics, we further propose named entity based metrics to evaluate the fidelity of D2T generations. Our experimental results show that R2D2 systems could effectively mitigate the unfaithful text generation, and they achieve new state-of-theart results on FeTaQA, LogicNLG, and ToTTo, all with significant improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nan-etal-2022-r2d2">
<titleInfo>
<title>R2D2: Robust Data-to-Text with Replacement Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linyong</namePart>
<namePart type="family">Nan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="given">Jaime</namePart>
<namePart type="family">Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Benson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijin</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unfaithful text generation is a common problem for text generation systems. In the case of Data-to-Text (D2T) systems, the factuality of the generated text is particularly crucial for any real-world applications. We introduce R2D2, a training framework that addresses unfaithful Data-to-Text generation by training a system both as a generator and a faithfulness discriminator with additional replacement detection and unlikelihood learning tasks. To facilitate such training, we propose two methods for sampling unfaithful sentences. We argue that the poor entity retrieval capability of D2T systems is one of the primary sources of unfaithfulness, so in addition to the existing metrics, we further propose named entity based metrics to evaluate the fidelity of D2T generations. Our experimental results show that R2D2 systems could effectively mitigate the unfaithful text generation, and they achieve new state-of-theart results on FeTaQA, LogicNLG, and ToTTo, all with significant improvements.</abstract>
<identifier type="citekey">nan-etal-2022-r2d2</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.464</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.464</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6903</start>
<end>6917</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T R2D2: Robust Data-to-Text with Replacement Detection
%A Nan, Linyong
%A Flores, Lorenzo Jaime
%A Zhao, Yilun
%A Liu, Yixin
%A Benson, Luke
%A Zou, Weijin
%A Radev, Dragomir
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F nan-etal-2022-r2d2
%X Unfaithful text generation is a common problem for text generation systems. In the case of Data-to-Text (D2T) systems, the factuality of the generated text is particularly crucial for any real-world applications. We introduce R2D2, a training framework that addresses unfaithful Data-to-Text generation by training a system both as a generator and a faithfulness discriminator with additional replacement detection and unlikelihood learning tasks. To facilitate such training, we propose two methods for sampling unfaithful sentences. We argue that the poor entity retrieval capability of D2T systems is one of the primary sources of unfaithfulness, so in addition to the existing metrics, we further propose named entity based metrics to evaluate the fidelity of D2T generations. Our experimental results show that R2D2 systems could effectively mitigate the unfaithful text generation, and they achieve new state-of-theart results on FeTaQA, LogicNLG, and ToTTo, all with significant improvements.
%R 10.18653/v1/2022.emnlp-main.464
%U https://aclanthology.org/2022.emnlp-main.464
%U https://doi.org/10.18653/v1/2022.emnlp-main.464
%P 6903-6917
Markdown (Informal)
[R2D2: Robust Data-to-Text with Replacement Detection](https://aclanthology.org/2022.emnlp-main.464) (Nan et al., EMNLP 2022)
ACL
- Linyong Nan, Lorenzo Jaime Flores, Yilun Zhao, Yixin Liu, Luke Benson, Weijin Zou, and Dragomir Radev. 2022. R2D2: Robust Data-to-Text with Replacement Detection. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6903–6917, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.