@inproceedings{steindl-etal-2024-counterfactual-dialog,
title = "Counterfactual Dialog Mixing as Data Augmentation for Task-Oriented Dialog Systems",
author = {Steindl, Sebastian and
Sch{\"a}fer, Ulrich and
Ludwig, Bernd},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.363",
pages = "4078--4087",
abstract = "High-quality training data for Task-Oriented Dialog (TOD) systems is costly to come by if no corpora are available. One method to extend available data is data augmentation. Yet, the research into and adaptation of data augmentation techniques for TOD systems is limited in comparison with other data modalities. We propose a novel, causally-flavored data augmentation technique called Counterfactual Dialog Mixing (CDM) that generates realistic synthetic dialogs via counterfactuals to increase the amount of training data. We demonstrate the method on a benchmark dataset and show that a model trained to classify the counterfactuals from the original data fails to do so, which strengthens the claim of creating realistic synthetic dialogs. To evaluate the effectiveness of CDM, we train a current architecture on a benchmark dataset and compare the performance with and without CDM. By doing so, we achieve state-of-the-art on some metrics. We further investigate the external generalizability and a lower resource setting. To evaluate the models, we adopted an interactive evaluation scheme.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steindl-etal-2024-counterfactual-dialog">
<titleInfo>
<title>Counterfactual Dialog Mixing as Data Augmentation for Task-Oriented Dialog Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Steindl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Schäfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernd</namePart>
<namePart type="family">Ludwig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>High-quality training data for Task-Oriented Dialog (TOD) systems is costly to come by if no corpora are available. One method to extend available data is data augmentation. Yet, the research into and adaptation of data augmentation techniques for TOD systems is limited in comparison with other data modalities. We propose a novel, causally-flavored data augmentation technique called Counterfactual Dialog Mixing (CDM) that generates realistic synthetic dialogs via counterfactuals to increase the amount of training data. We demonstrate the method on a benchmark dataset and show that a model trained to classify the counterfactuals from the original data fails to do so, which strengthens the claim of creating realistic synthetic dialogs. To evaluate the effectiveness of CDM, we train a current architecture on a benchmark dataset and compare the performance with and without CDM. By doing so, we achieve state-of-the-art on some metrics. We further investigate the external generalizability and a lower resource setting. To evaluate the models, we adopted an interactive evaluation scheme.</abstract>
<identifier type="citekey">steindl-etal-2024-counterfactual-dialog</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.363</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4078</start>
<end>4087</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Counterfactual Dialog Mixing as Data Augmentation for Task-Oriented Dialog Systems
%A Steindl, Sebastian
%A Schäfer, Ulrich
%A Ludwig, Bernd
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F steindl-etal-2024-counterfactual-dialog
%X High-quality training data for Task-Oriented Dialog (TOD) systems is costly to come by if no corpora are available. One method to extend available data is data augmentation. Yet, the research into and adaptation of data augmentation techniques for TOD systems is limited in comparison with other data modalities. We propose a novel, causally-flavored data augmentation technique called Counterfactual Dialog Mixing (CDM) that generates realistic synthetic dialogs via counterfactuals to increase the amount of training data. We demonstrate the method on a benchmark dataset and show that a model trained to classify the counterfactuals from the original data fails to do so, which strengthens the claim of creating realistic synthetic dialogs. To evaluate the effectiveness of CDM, we train a current architecture on a benchmark dataset and compare the performance with and without CDM. By doing so, we achieve state-of-the-art on some metrics. We further investigate the external generalizability and a lower resource setting. To evaluate the models, we adopted an interactive evaluation scheme.
%U https://aclanthology.org/2024.lrec-main.363
%P 4078-4087
Markdown (Informal)
[Counterfactual Dialog Mixing as Data Augmentation for Task-Oriented Dialog Systems](https://aclanthology.org/2024.lrec-main.363) (Steindl et al., LREC-COLING 2024)
ACL