@inproceedings{petrak-etal-2023-learning,
title = "Learning From Free-Text Human Feedback {--} Collect New Datasets Or Extend Existing Ones?",
author = "Petrak, Dominic and
Moosavi, Nafise and
Tian, Ye and
Rozanov, Nikolai and
Gurevych, Iryna",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.1011/",
doi = "10.18653/v1/2023.emnlp-main.1011",
pages = "16259--16279",
abstract = "Continuous learning from free-text human feedback, such as error corrections, new knowledge, or alternative responses, is essential for today`s chatbots and virtual assistants to stay up-to-date, engaging, and socially acceptable. However, for research on methods for learning from such data, annotated data is scarce. To address this, we examine the error and user response types of six popular dialogue datasets from various types, including MultiWoZ, PersonaChat, Wizards-of-Wikipedia, and others, to assess their extendibility with the needed annotations. For this corpus study, we manually annotate a subset of each dataset with error and user response types using an improved version of the Integrated Error Taxonomy and a newly proposed user response type taxonomy. We provide the resulting dataset (EURTAD) to the community. Our findings provide new insights into dataset composition, including error types, user response types, and the relations between them."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petrak-etal-2023-learning">
<titleInfo>
<title>Learning From Free-Text Human Feedback – Collect New Datasets Or Extend Existing Ones?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominic</namePart>
<namePart type="family">Petrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Continuous learning from free-text human feedback, such as error corrections, new knowledge, or alternative responses, is essential for today‘s chatbots and virtual assistants to stay up-to-date, engaging, and socially acceptable. However, for research on methods for learning from such data, annotated data is scarce. To address this, we examine the error and user response types of six popular dialogue datasets from various types, including MultiWoZ, PersonaChat, Wizards-of-Wikipedia, and others, to assess their extendibility with the needed annotations. For this corpus study, we manually annotate a subset of each dataset with error and user response types using an improved version of the Integrated Error Taxonomy and a newly proposed user response type taxonomy. We provide the resulting dataset (EURTAD) to the community. Our findings provide new insights into dataset composition, including error types, user response types, and the relations between them.</abstract>
<identifier type="citekey">petrak-etal-2023-learning</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.1011</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.1011/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>16259</start>
<end>16279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning From Free-Text Human Feedback – Collect New Datasets Or Extend Existing Ones?
%A Petrak, Dominic
%A Moosavi, Nafise
%A Tian, Ye
%A Rozanov, Nikolai
%A Gurevych, Iryna
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F petrak-etal-2023-learning
%X Continuous learning from free-text human feedback, such as error corrections, new knowledge, or alternative responses, is essential for today‘s chatbots and virtual assistants to stay up-to-date, engaging, and socially acceptable. However, for research on methods for learning from such data, annotated data is scarce. To address this, we examine the error and user response types of six popular dialogue datasets from various types, including MultiWoZ, PersonaChat, Wizards-of-Wikipedia, and others, to assess their extendibility with the needed annotations. For this corpus study, we manually annotate a subset of each dataset with error and user response types using an improved version of the Integrated Error Taxonomy and a newly proposed user response type taxonomy. We provide the resulting dataset (EURTAD) to the community. Our findings provide new insights into dataset composition, including error types, user response types, and the relations between them.
%R 10.18653/v1/2023.emnlp-main.1011
%U https://aclanthology.org/2023.emnlp-main.1011/
%U https://doi.org/10.18653/v1/2023.emnlp-main.1011
%P 16259-16279
Markdown (Informal)
[Learning From Free-Text Human Feedback – Collect New Datasets Or Extend Existing Ones?](https://aclanthology.org/2023.emnlp-main.1011/) (Petrak et al., EMNLP 2023)
ACL