@inproceedings{yoon-etal-2022-building,
title = "Building {K}orean Linguistic Resource for {NLU} Data Generation of Banking App {CS} Dialog System",
author = "Yoon, Jeongwoo and
Park, Onyu and
Hwang, Changhoe and
Yoo, Gwanghoon and
Laporte, Eric and
Nam, Jeesun",
editor = "Chiticariu, Laura and
Goldberg, Yoav and
Hahn-Powell, Gus and
Morrison, Clayton T. and
Naik, Aakanksha and
Sharp, Rebecca and
Surdeanu, Mihai and
Valenzuela-Esc{\'a}rcega, Marco and
Noriega-Atala, Enrique",
booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.pandl-1.4",
pages = "29--37",
abstract = "Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increase the coverage of diverse utterances. In this study, we report the construction of a linguistic resource named FIAD (Financial Annotated Dataset) and its use to generate a Korean annotated training data for NLU in the banking customer service (CS) domain. By an empirical examination of a corpus of banking app reviews, we identified three linguistic patterns occurring in Korean request utterances: TOPIC (ENTITY, FEATURE), EVENT, and DISCOURSE MARKER. We represented them in LGGs (Local Grammar Graphs) to generate annotated data covering diverse intents and entities. To assess the practicality of the resource, we evaluate the performances of DIET-only (Intent: 0.91 /Topic [entity+feature]: 0.83), DIET+ HANBERT (I:0.94/T:0.85), DIET+ KoBERT (I:0.94/T:0.86), and DIET+ KorBERT (I:0.95/T:0.84) models trained on FIAD-generated data to extract various types of semantic items.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoon-etal-2022-building">
<titleInfo>
<title>Building Korean Linguistic Resource for NLU Data Generation of Banking App CS Dialog System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeongwoo</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onyu</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changhoe</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gwanghoon</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Laporte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeesun</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Chiticariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Gus</namePart>
<namePart type="family">Hahn-Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clayton</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Morrison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sharp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valenzuela-Escárcega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increase the coverage of diverse utterances. In this study, we report the construction of a linguistic resource named FIAD (Financial Annotated Dataset) and its use to generate a Korean annotated training data for NLU in the banking customer service (CS) domain. By an empirical examination of a corpus of banking app reviews, we identified three linguistic patterns occurring in Korean request utterances: TOPIC (ENTITY, FEATURE), EVENT, and DISCOURSE MARKER. We represented them in LGGs (Local Grammar Graphs) to generate annotated data covering diverse intents and entities. To assess the practicality of the resource, we evaluate the performances of DIET-only (Intent: 0.91 /Topic [entity+feature]: 0.83), DIET+ HANBERT (I:0.94/T:0.85), DIET+ KoBERT (I:0.94/T:0.86), and DIET+ KorBERT (I:0.95/T:0.84) models trained on FIAD-generated data to extract various types of semantic items.</abstract>
<identifier type="citekey">yoon-etal-2022-building</identifier>
<location>
<url>https://aclanthology.org/2022.pandl-1.4</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>29</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Korean Linguistic Resource for NLU Data Generation of Banking App CS Dialog System
%A Yoon, Jeongwoo
%A Park, Onyu
%A Hwang, Changhoe
%A Yoo, Gwanghoon
%A Laporte, Eric
%A Nam, Jeesun
%Y Chiticariu, Laura
%Y Goldberg, Yoav
%Y Hahn-Powell, Gus
%Y Morrison, Clayton T.
%Y Naik, Aakanksha
%Y Sharp, Rebecca
%Y Surdeanu, Mihai
%Y Valenzuela-Escárcega, Marco
%Y Noriega-Atala, Enrique
%S Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, Republic of Korea
%F yoon-etal-2022-building
%X Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increase the coverage of diverse utterances. In this study, we report the construction of a linguistic resource named FIAD (Financial Annotated Dataset) and its use to generate a Korean annotated training data for NLU in the banking customer service (CS) domain. By an empirical examination of a corpus of banking app reviews, we identified three linguistic patterns occurring in Korean request utterances: TOPIC (ENTITY, FEATURE), EVENT, and DISCOURSE MARKER. We represented them in LGGs (Local Grammar Graphs) to generate annotated data covering diverse intents and entities. To assess the practicality of the resource, we evaluate the performances of DIET-only (Intent: 0.91 /Topic [entity+feature]: 0.83), DIET+ HANBERT (I:0.94/T:0.85), DIET+ KoBERT (I:0.94/T:0.86), and DIET+ KorBERT (I:0.95/T:0.84) models trained on FIAD-generated data to extract various types of semantic items.
%U https://aclanthology.org/2022.pandl-1.4
%P 29-37
Markdown (Informal)
[Building Korean Linguistic Resource for NLU Data Generation of Banking App CS Dialog System](https://aclanthology.org/2022.pandl-1.4) (Yoon et al., PANDL 2022)
ACL