@inproceedings{choi-etal-2022-kildst,
title = "{KILDST}: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information",
author = "Choi, Hyungtak and
Ko, Hyeonmok and
Kaur, Gurpreet and
Ravuru, Lohith and
Gandikota, Kiranmayi and
Jhawar, Manisha and
Dharani, Simma and
Patil, Pranamya",
editor = "Akhtar, Md. Shad and
Chakraborty, Tanmoy",
booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2022",
address = "New Delhi, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.icon-main.8",
pages = "60--66",
abstract = "Dialogue State Tracking (DST) is core research in dialogue systems and has received much attention. In addition, it is necessary to define a new problem that can deal with dialogue between users as a step toward the conversational AI that extracts and recommends information from the dialogue between users. So, we introduce a new task - DST from dialogue between users about scheduling an event (DST-USERS). The DST-USERS task is much more challenging since it requires the model to understand and track dialogue states in the dialogue between users, as well as to understand who suggested the schedule and who agreed to the proposed schedule. To facilitate DST-USERS research, we develop dialogue datasets between users that plan a schedule. The annotated slot values which need to be extracted in the dialogue are date, time, and location. Previous approaches, such as Machine Reading Comprehension (MRC) and traditional DST techniques, have not achieved good results in our extensive evaluations. By adopting the knowledge-integrated learning method, we achieve exceptional results. The proposed model architecture combines gazetteer features and speaker information efficiently. Our evaluations of the dialogue datasets between users that plan a schedule show that our model outperforms the baseline model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2022-kildst">
<titleInfo>
<title>KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyungtak</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeonmok</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gurpreet</namePart>
<namePart type="family">Kaur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lohith</namePart>
<namePart type="family">Ravuru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiranmayi</namePart>
<namePart type="family">Gandikota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manisha</namePart>
<namePart type="family">Jhawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simma</namePart>
<namePart type="family">Dharani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranamya</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Delhi, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue State Tracking (DST) is core research in dialogue systems and has received much attention. In addition, it is necessary to define a new problem that can deal with dialogue between users as a step toward the conversational AI that extracts and recommends information from the dialogue between users. So, we introduce a new task - DST from dialogue between users about scheduling an event (DST-USERS). The DST-USERS task is much more challenging since it requires the model to understand and track dialogue states in the dialogue between users, as well as to understand who suggested the schedule and who agreed to the proposed schedule. To facilitate DST-USERS research, we develop dialogue datasets between users that plan a schedule. The annotated slot values which need to be extracted in the dialogue are date, time, and location. Previous approaches, such as Machine Reading Comprehension (MRC) and traditional DST techniques, have not achieved good results in our extensive evaluations. By adopting the knowledge-integrated learning method, we achieve exceptional results. The proposed model architecture combines gazetteer features and speaker information efficiently. Our evaluations of the dialogue datasets between users that plan a schedule show that our model outperforms the baseline model.</abstract>
<identifier type="citekey">choi-etal-2022-kildst</identifier>
<location>
<url>https://aclanthology.org/2022.icon-main.8</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>60</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information
%A Choi, Hyungtak
%A Ko, Hyeonmok
%A Kaur, Gurpreet
%A Ravuru, Lohith
%A Gandikota, Kiranmayi
%A Jhawar, Manisha
%A Dharani, Simma
%A Patil, Pranamya
%Y Akhtar, Md. Shad
%Y Chakraborty, Tanmoy
%S Proceedings of the 19th International Conference on Natural Language Processing (ICON)
%D 2022
%8 December
%I Association for Computational Linguistics
%C New Delhi, India
%F choi-etal-2022-kildst
%X Dialogue State Tracking (DST) is core research in dialogue systems and has received much attention. In addition, it is necessary to define a new problem that can deal with dialogue between users as a step toward the conversational AI that extracts and recommends information from the dialogue between users. So, we introduce a new task - DST from dialogue between users about scheduling an event (DST-USERS). The DST-USERS task is much more challenging since it requires the model to understand and track dialogue states in the dialogue between users, as well as to understand who suggested the schedule and who agreed to the proposed schedule. To facilitate DST-USERS research, we develop dialogue datasets between users that plan a schedule. The annotated slot values which need to be extracted in the dialogue are date, time, and location. Previous approaches, such as Machine Reading Comprehension (MRC) and traditional DST techniques, have not achieved good results in our extensive evaluations. By adopting the knowledge-integrated learning method, we achieve exceptional results. The proposed model architecture combines gazetteer features and speaker information efficiently. Our evaluations of the dialogue datasets between users that plan a schedule show that our model outperforms the baseline model.
%U https://aclanthology.org/2022.icon-main.8
%P 60-66
Markdown (Informal)
[KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information](https://aclanthology.org/2022.icon-main.8) (Choi et al., ICON 2022)
ACL
- Hyungtak Choi, Hyeonmok Ko, Gurpreet Kaur, Lohith Ravuru, Kiranmayi Gandikota, Manisha Jhawar, Simma Dharani, and Pranamya Patil. 2022. KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information. In Proceedings of the 19th International Conference on Natural Language Processing (ICON), pages 60–66, New Delhi, India. Association for Computational Linguistics.