Domain State Tracking for a Simplified Dialogue System
Task-oriented dialogue systems aim to help users achieve their goals in specific domains. Recent neural dialogue systems use the entire dialogue history for abundant contextual information accumulated over multiple conversational turns. However, the dialogue history becomes increasingly longer as th...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Jeon, Hyunmin Lee, Gary Geunbae |
| description | Task-oriented dialogue systems aim to help users achieve their goals in
specific domains. Recent neural dialogue systems use the entire dialogue
history for abundant contextual information accumulated over multiple
conversational turns. However, the dialogue history becomes increasingly longer
as the number of turns increases, thereby increasing memory usage and
computational costs. In this paper, we present DoTS (Domain State Tracking for
a Simplified Dialogue System), a task-oriented dialogue system that uses a
simplified input context instead of the entire dialogue history. However,
neglecting the dialogue history can result in a loss of contextual information
from previous conversational turns. To address this issue, DoTS tracks the
domain state in addition to the belief state and uses it for the input context.
Using this simplified input, DoTS improves the inform rate and success rate by
1.09 points and 1.24 points, respectively, compared to the previous
state-of-the-art model on MultiWOZ, which is a well-known benchmark. |
| doi_str_mv | 10.48550/arxiv.2103.06648 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2103_06648</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2103_06648</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-add7a2e4bff4f0e603a59ba8945f6ea94c13e327aa1a309d5789e6416c058da93</originalsourceid><addsrcrecordid>eNotj7tuwjAYRr0wVNAH6FS_QFI7vsQeK6AXCalDskcf8W9kNSHIpKi8fVXa6WxH5zD2IEWpnTHiCfk7XcpKClUKa7W7Y3YzjUhH3syYibcZ_Wc6HnicMgdv0ngaUkwU-CZhmA5fxJvreaZxxRYRw5nu_7lk7cu2Xb8Vu4_X9_XzroCtXYEQalSk9zHqKMgKBeP3cF6baAle91KRqmpAQgkfTO08WS1tL4wL8GrJHv-0t_DulNOIfO1-B7rbgPoB0WE_7g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Domain State Tracking for a Simplified Dialogue System</title><source>arXiv.org</source><creator>Jeon, Hyunmin ; Lee, Gary Geunbae</creator><creatorcontrib>Jeon, Hyunmin ; Lee, Gary Geunbae</creatorcontrib><description>Task-oriented dialogue systems aim to help users achieve their goals in
specific domains. Recent neural dialogue systems use the entire dialogue
history for abundant contextual information accumulated over multiple
conversational turns. However, the dialogue history becomes increasingly longer
as the number of turns increases, thereby increasing memory usage and
computational costs. In this paper, we present DoTS (Domain State Tracking for
a Simplified Dialogue System), a task-oriented dialogue system that uses a
simplified input context instead of the entire dialogue history. However,
neglecting the dialogue history can result in a loss of contextual information
from previous conversational turns. To address this issue, DoTS tracks the
domain state in addition to the belief state and uses it for the input context.
Using this simplified input, DoTS improves the inform rate and success rate by
1.09 points and 1.24 points, respectively, compared to the previous
state-of-the-art model on MultiWOZ, which is a well-known benchmark.</description><identifier>DOI: 10.48550/arxiv.2103.06648</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2021-03</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2103.06648$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2103.06648$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Jeon, Hyunmin</creatorcontrib><creatorcontrib>Lee, Gary Geunbae</creatorcontrib><title>Domain State Tracking for a Simplified Dialogue System</title><description>Task-oriented dialogue systems aim to help users achieve their goals in
specific domains. Recent neural dialogue systems use the entire dialogue
history for abundant contextual information accumulated over multiple
conversational turns. However, the dialogue history becomes increasingly longer
as the number of turns increases, thereby increasing memory usage and
computational costs. In this paper, we present DoTS (Domain State Tracking for
a Simplified Dialogue System), a task-oriented dialogue system that uses a
simplified input context instead of the entire dialogue history. However,
neglecting the dialogue history can result in a loss of contextual information
from previous conversational turns. To address this issue, DoTS tracks the
domain state in addition to the belief state and uses it for the input context.
Using this simplified input, DoTS improves the inform rate and success rate by
1.09 points and 1.24 points, respectively, compared to the previous
state-of-the-art model on MultiWOZ, which is a well-known benchmark.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tuwjAYRr0wVNAH6FS_QFI7vsQeK6AXCalDskcf8W9kNSHIpKi8fVXa6WxH5zD2IEWpnTHiCfk7XcpKClUKa7W7Y3YzjUhH3syYibcZ_Wc6HnicMgdv0ngaUkwU-CZhmA5fxJvreaZxxRYRw5nu_7lk7cu2Xb8Vu4_X9_XzroCtXYEQalSk9zHqKMgKBeP3cF6baAle91KRqmpAQgkfTO08WS1tL4wL8GrJHv-0t_DulNOIfO1-B7rbgPoB0WE_7g</recordid><startdate>20210311</startdate><enddate>20210311</enddate><creator>Jeon, Hyunmin</creator><creator>Lee, Gary Geunbae</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210311</creationdate><title>Domain State Tracking for a Simplified Dialogue System</title><author>Jeon, Hyunmin ; Lee, Gary Geunbae</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-add7a2e4bff4f0e603a59ba8945f6ea94c13e327aa1a309d5789e6416c058da93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Jeon, Hyunmin</creatorcontrib><creatorcontrib>Lee, Gary Geunbae</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jeon, Hyunmin</au><au>Lee, Gary Geunbae</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Domain State Tracking for a Simplified Dialogue System</atitle><date>2021-03-11</date><risdate>2021</risdate><abstract>Task-oriented dialogue systems aim to help users achieve their goals in
specific domains. Recent neural dialogue systems use the entire dialogue
history for abundant contextual information accumulated over multiple
conversational turns. However, the dialogue history becomes increasingly longer
as the number of turns increases, thereby increasing memory usage and
computational costs. In this paper, we present DoTS (Domain State Tracking for
a Simplified Dialogue System), a task-oriented dialogue system that uses a
simplified input context instead of the entire dialogue history. However,
neglecting the dialogue history can result in a loss of contextual information
from previous conversational turns. To address this issue, DoTS tracks the
domain state in addition to the belief state and uses it for the input context.
Using this simplified input, DoTS improves the inform rate and success rate by
1.09 points and 1.24 points, respectively, compared to the previous
state-of-the-art model on MultiWOZ, which is a well-known benchmark.</abstract><doi>10.48550/arxiv.2103.06648</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2103.06648 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2103_06648 |
| source | arXiv.org |
| subjects | Computer Science - Computation and Language |
| title | Domain State Tracking for a Simplified Dialogue System |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T23%3A46%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Domain%20State%20Tracking%20for%20a%20Simplified%20Dialogue%20System&rft.au=Jeon,%20Hyunmin&rft.date=2021-03-11&rft_id=info:doi/10.48550/arxiv.2103.06648&rft_dat=%3Carxiv_GOX%3E2103_06648%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |