@inproceedings{lee-etal-2023-semantic,
title = "Semantic data augmentation for meaning maintenance on Task-Oriented Conversation with Large-size Language Model",
author = "Lee, Jaehwan and
Son, Kwanyoung and
Kim, Eugene",
editor = "Chen, Yun-Nung and
Crook, Paul and
Galley, Michel and
Ghazarian, Sarik and
Gunasekara, Chulaka and
Gupta, Raghav and
Hedayatnia, Behnam and
Kottur, Satwik and
Moon, Seungwhan and
Zhang, Chen",
booktitle = "Proceedings of The Eleventh Dialog System Technology Challenge",
month = sep,
year = "2023",
address = "Prague, Czech Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dstc-1.19",
pages = "166--176",
abstract = "This paper presents our approach to building a generalized model for Track 5 in DSTC11: {``}Task-oriented Conversational Modeling with Subjective Knowledge{''} which addresses the challenge of generating responses to users{'} utterances based on a variety of factual and subjective knowledge. To tackle this challenge, we first augmented the training data by leveraging contextual word embedding and back translation, thereby increasing the quantity of available data. Then, we utilized a large-size language model to enhance the acceptability of the augmented data and fine-tuned the model using augmented data. Specifically, we applied the DeBERTa-v3-large model for knowledge detection and selection, and the BART-large model for response generation. Our best model achieved the seventh rank in the objective evaluation and the second rank in the final official human evaluation. These outcomes serve as solid evidence that data augmentation and using a large-size model were highly effective for developing a conversational model system that incorporates objective and subjective knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2023-semantic">
<titleInfo>
<title>Semantic data augmentation for meaning maintenance on Task-Oriented Conversation with Large-size Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaehwan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kwanyoung</namePart>
<namePart type="family">Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Eleventh Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Kottur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</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">Prague, Czech Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our approach to building a generalized model for Track 5 in DSTC11: “Task-oriented Conversational Modeling with Subjective Knowledge” which addresses the challenge of generating responses to users’ utterances based on a variety of factual and subjective knowledge. To tackle this challenge, we first augmented the training data by leveraging contextual word embedding and back translation, thereby increasing the quantity of available data. Then, we utilized a large-size language model to enhance the acceptability of the augmented data and fine-tuned the model using augmented data. Specifically, we applied the DeBERTa-v3-large model for knowledge detection and selection, and the BART-large model for response generation. Our best model achieved the seventh rank in the objective evaluation and the second rank in the final official human evaluation. These outcomes serve as solid evidence that data augmentation and using a large-size model were highly effective for developing a conversational model system that incorporates objective and subjective knowledge.</abstract>
<identifier type="citekey">lee-etal-2023-semantic</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.19</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>166</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic data augmentation for meaning maintenance on Task-Oriented Conversation with Large-size Language Model
%A Lee, Jaehwan
%A Son, Kwanyoung
%A Kim, Eugene
%Y Chen, Yun-Nung
%Y Crook, Paul
%Y Galley, Michel
%Y Ghazarian, Sarik
%Y Gunasekara, Chulaka
%Y Gupta, Raghav
%Y Hedayatnia, Behnam
%Y Kottur, Satwik
%Y Moon, Seungwhan
%Y Zhang, Chen
%S Proceedings of The Eleventh Dialog System Technology Challenge
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F lee-etal-2023-semantic
%X This paper presents our approach to building a generalized model for Track 5 in DSTC11: “Task-oriented Conversational Modeling with Subjective Knowledge” which addresses the challenge of generating responses to users’ utterances based on a variety of factual and subjective knowledge. To tackle this challenge, we first augmented the training data by leveraging contextual word embedding and back translation, thereby increasing the quantity of available data. Then, we utilized a large-size language model to enhance the acceptability of the augmented data and fine-tuned the model using augmented data. Specifically, we applied the DeBERTa-v3-large model for knowledge detection and selection, and the BART-large model for response generation. Our best model achieved the seventh rank in the objective evaluation and the second rank in the final official human evaluation. These outcomes serve as solid evidence that data augmentation and using a large-size model were highly effective for developing a conversational model system that incorporates objective and subjective knowledge.
%U https://aclanthology.org/2023.dstc-1.19
%P 166-176
Markdown (Informal)
[Semantic data augmentation for meaning maintenance on Task-Oriented Conversation with Large-size Language Model](https://aclanthology.org/2023.dstc-1.19) (Lee et al., DSTC-WS 2023)
ACL