@inproceedings{peng-etal-2021-raddle,
title = "{RADDLE}: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems",
author = "Peng, Baolin and
Li, Chunyuan and
Zhang, Zhu and
Zhu, Chenguang and
Li, Jinchao and
Gao, Jianfeng",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
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.341",
doi = "10.18653/v1/2021.acl-long.341",
pages = "4418--4429",
abstract = "For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities, or domains. In pursuit of these goals, we introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. By including tasks with limited training data, RADDLE is designed to favor and encourage models with a strong generalization ability. RADDLE also includes a diagnostic checklist that facilitates detailed robustness analysis in aspects such as language variations, speech errors, unseen entities, and out-of-domain utterances. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain. Adversarial training is also proposed to improve model robustness against noisy inputs. Overall, existing models are less than satisfactory in robustness evaluation, which suggests opportunities for future improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2021-raddle">
<titleInfo>
<title>RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baolin</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenguang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinchao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</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>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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 task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities, or domains. In pursuit of these goals, we introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. By including tasks with limited training data, RADDLE is designed to favor and encourage models with a strong generalization ability. RADDLE also includes a diagnostic checklist that facilitates detailed robustness analysis in aspects such as language variations, speech errors, unseen entities, and out-of-domain utterances. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain. Adversarial training is also proposed to improve model robustness against noisy inputs. Overall, existing models are less than satisfactory in robustness evaluation, which suggests opportunities for future improvement.</abstract>
<identifier type="citekey">peng-etal-2021-raddle</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.341</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.341</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4418</start>
<end>4429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems
%A Peng, Baolin
%A Li, Chunyuan
%A Zhang, Zhu
%A Zhu, Chenguang
%A Li, Jinchao
%A Gao, Jianfeng
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%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 August
%I Association for Computational Linguistics
%C Online
%F peng-etal-2021-raddle
%X For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities, or domains. In pursuit of these goals, we introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. By including tasks with limited training data, RADDLE is designed to favor and encourage models with a strong generalization ability. RADDLE also includes a diagnostic checklist that facilitates detailed robustness analysis in aspects such as language variations, speech errors, unseen entities, and out-of-domain utterances. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain. Adversarial training is also proposed to improve model robustness against noisy inputs. Overall, existing models are less than satisfactory in robustness evaluation, which suggests opportunities for future improvement.
%R 10.18653/v1/2021.acl-long.341
%U https://aclanthology.org/2021.acl-long.341
%U https://doi.org/10.18653/v1/2021.acl-long.341
%P 4418-4429
Markdown (Informal)
[RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems](https://aclanthology.org/2021.acl-long.341) (Peng et al., ACL-IJCNLP 2021)
ACL