Loading…
Intent Recognition on Low-Resource Language Messages in a Health Marketplace Chatbot
In this paper we explore intent recognition models of user messages sent to a chatbot that primarily uses system-initiated navigation. The chatbot (askNivi) discusses sexual and reproductive health topics for educational purposes and to facilitate healthcare access. It is deployed in four languages,...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 459 |
| container_issue | |
| container_start_page | 457 |
| container_title | |
| container_volume | |
| creator | Tresner-Kirsch, David Mikkelson, Amanda Azari Yinka-Banjo, Chika Akinyemi, Mary Goyal, Siddhartha |
| description | In this paper we explore intent recognition models of user messages sent to a chatbot that primarily uses system-initiated navigation. The chatbot (askNivi) discusses sexual and reproductive health topics for educational purposes and to facilitate healthcare access. It is deployed in four languages, three of which are considered low-resource languages (Hausa, Hindi, and Swahili; the fourth language is English). Although the primary navigation mode is system-initiated, many users attempt to take initiative by expressing various intents with natural language messages. This paper describes a multi-lingual corpus of those initiative attempts manually annotated with intent labels as well as results of modeling experiments on the classification of these intents using context-dependent supervised machine learning. |
| doi_str_mv | 10.1109/ICHI57859.2023.00066 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10337283</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10337283</ieee_id><sourcerecordid>10337283</sourcerecordid><originalsourceid>FETCH-LOGICAL-i119t-14847b8bf1dc5355e1d22910ca9d85732646538050f72bc4ffe2ded9d4caf82f3</originalsourceid><addsrcrecordid>eNotjNFKwzAUhqMgOGbfYBd5gc6TnKZJLqWoK3QIY16PtD3pqrUdTYb49hYUfvj-i4-PsY2ArRBgH8tiVyptlN1KkLgFgDy_YYnV1qACBJmjvWUrqbRKl5_dsySEj0VDYRcXVuxYjpHGyA_UTN3Yx34a-bJq-k4PFKbr3BCv3NhdXUd8TyEsDLwfueM7ckM8872bPyleBreYxdnFeooP7M67IVDyzzV7f3k-Fru0ensti6cq7YWwMRWZyXRtai_aRqFSJFoprYDG2dYojTLPcoUGFHgt6ybznmRLrW2zxnkjPa7Z5q_bE9HpMvdfbv45CUDU0iD-AiWCUbQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Intent Recognition on Low-Resource Language Messages in a Health Marketplace Chatbot</title><source>IEEE Xplore All Conference Series</source><creator>Tresner-Kirsch, David ; Mikkelson, Amanda Azari ; Yinka-Banjo, Chika ; Akinyemi, Mary ; Goyal, Siddhartha</creator><creatorcontrib>Tresner-Kirsch, David ; Mikkelson, Amanda Azari ; Yinka-Banjo, Chika ; Akinyemi, Mary ; Goyal, Siddhartha</creatorcontrib><description>In this paper we explore intent recognition models of user messages sent to a chatbot that primarily uses system-initiated navigation. The chatbot (askNivi) discusses sexual and reproductive health topics for educational purposes and to facilitate healthcare access. It is deployed in four languages, three of which are considered low-resource languages (Hausa, Hindi, and Swahili; the fourth language is English). Although the primary navigation mode is system-initiated, many users attempt to take initiative by expressing various intents with natural language messages. This paper describes a multi-lingual corpus of those initiative attempts manually annotated with intent labels as well as results of modeling experiments on the classification of these intents using context-dependent supervised machine learning.</description><identifier>EISSN: 2575-2634</identifier><identifier>EISBN: 9798350302639</identifier><identifier>DOI: 10.1109/ICHI57859.2023.00066</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Chatbots ; Context modeling ; dialogue systems ; Informatics ; intent recognition ; Machine learning ; Medical services ; Natural Language Processing (NLP) ; Navigation ; sexual and reproductive health</subject><ispartof>2023 IEEE 11th International Conference on Healthcare Informatics (ICHI), 2023, p.457-459</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10337283$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10337283$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Tresner-Kirsch, David</creatorcontrib><creatorcontrib>Mikkelson, Amanda Azari</creatorcontrib><creatorcontrib>Yinka-Banjo, Chika</creatorcontrib><creatorcontrib>Akinyemi, Mary</creatorcontrib><creatorcontrib>Goyal, Siddhartha</creatorcontrib><title>Intent Recognition on Low-Resource Language Messages in a Health Marketplace Chatbot</title><title>2023 IEEE 11th International Conference on Healthcare Informatics (ICHI)</title><addtitle>ICHI</addtitle><description>In this paper we explore intent recognition models of user messages sent to a chatbot that primarily uses system-initiated navigation. The chatbot (askNivi) discusses sexual and reproductive health topics for educational purposes and to facilitate healthcare access. It is deployed in four languages, three of which are considered low-resource languages (Hausa, Hindi, and Swahili; the fourth language is English). Although the primary navigation mode is system-initiated, many users attempt to take initiative by expressing various intents with natural language messages. This paper describes a multi-lingual corpus of those initiative attempts manually annotated with intent labels as well as results of modeling experiments on the classification of these intents using context-dependent supervised machine learning.</description><subject>Chatbots</subject><subject>Context modeling</subject><subject>dialogue systems</subject><subject>Informatics</subject><subject>intent recognition</subject><subject>Machine learning</subject><subject>Medical services</subject><subject>Natural Language Processing (NLP)</subject><subject>Navigation</subject><subject>sexual and reproductive health</subject><issn>2575-2634</issn><isbn>9798350302639</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjNFKwzAUhqMgOGbfYBd5gc6TnKZJLqWoK3QIY16PtD3pqrUdTYb49hYUfvj-i4-PsY2ArRBgH8tiVyptlN1KkLgFgDy_YYnV1qACBJmjvWUrqbRKl5_dsySEj0VDYRcXVuxYjpHGyA_UTN3Yx34a-bJq-k4PFKbr3BCv3NhdXUd8TyEsDLwfueM7ckM8872bPyleBreYxdnFeooP7M67IVDyzzV7f3k-Fru0ensti6cq7YWwMRWZyXRtai_aRqFSJFoprYDG2dYojTLPcoUGFHgt6ybznmRLrW2zxnkjPa7Z5q_bE9HpMvdfbv45CUDU0iD-AiWCUbQ</recordid><startdate>20230626</startdate><enddate>20230626</enddate><creator>Tresner-Kirsch, David</creator><creator>Mikkelson, Amanda Azari</creator><creator>Yinka-Banjo, Chika</creator><creator>Akinyemi, Mary</creator><creator>Goyal, Siddhartha</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20230626</creationdate><title>Intent Recognition on Low-Resource Language Messages in a Health Marketplace Chatbot</title><author>Tresner-Kirsch, David ; Mikkelson, Amanda Azari ; Yinka-Banjo, Chika ; Akinyemi, Mary ; Goyal, Siddhartha</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i119t-14847b8bf1dc5355e1d22910ca9d85732646538050f72bc4ffe2ded9d4caf82f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Chatbots</topic><topic>Context modeling</topic><topic>dialogue systems</topic><topic>Informatics</topic><topic>intent recognition</topic><topic>Machine learning</topic><topic>Medical services</topic><topic>Natural Language Processing (NLP)</topic><topic>Navigation</topic><topic>sexual and reproductive health</topic><toplevel>online_resources</toplevel><creatorcontrib>Tresner-Kirsch, David</creatorcontrib><creatorcontrib>Mikkelson, Amanda Azari</creatorcontrib><creatorcontrib>Yinka-Banjo, Chika</creatorcontrib><creatorcontrib>Akinyemi, Mary</creatorcontrib><creatorcontrib>Goyal, Siddhartha</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tresner-Kirsch, David</au><au>Mikkelson, Amanda Azari</au><au>Yinka-Banjo, Chika</au><au>Akinyemi, Mary</au><au>Goyal, Siddhartha</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Intent Recognition on Low-Resource Language Messages in a Health Marketplace Chatbot</atitle><btitle>2023 IEEE 11th International Conference on Healthcare Informatics (ICHI)</btitle><stitle>ICHI</stitle><date>2023-06-26</date><risdate>2023</risdate><spage>457</spage><epage>459</epage><pages>457-459</pages><eissn>2575-2634</eissn><eisbn>9798350302639</eisbn><coden>IEEPAD</coden><abstract>In this paper we explore intent recognition models of user messages sent to a chatbot that primarily uses system-initiated navigation. The chatbot (askNivi) discusses sexual and reproductive health topics for educational purposes and to facilitate healthcare access. It is deployed in four languages, three of which are considered low-resource languages (Hausa, Hindi, and Swahili; the fourth language is English). Although the primary navigation mode is system-initiated, many users attempt to take initiative by expressing various intents with natural language messages. This paper describes a multi-lingual corpus of those initiative attempts manually annotated with intent labels as well as results of modeling experiments on the classification of these intents using context-dependent supervised machine learning.</abstract><pub>IEEE</pub><doi>10.1109/ICHI57859.2023.00066</doi><tpages>3</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2575-2634 |
| ispartof | 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI), 2023, p.457-459 |
| issn | 2575-2634 |
| language | eng |
| recordid | cdi_ieee_primary_10337283 |
| source | IEEE Xplore All Conference Series |
| subjects | Chatbots Context modeling dialogue systems Informatics intent recognition Machine learning Medical services Natural Language Processing (NLP) Navigation sexual and reproductive health |
| title | Intent Recognition on Low-Resource Language Messages in a Health Marketplace Chatbot |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T17%3A59%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Intent%20Recognition%20on%20Low-Resource%20Language%20Messages%20in%20a%20Health%20Marketplace%20Chatbot&rft.btitle=2023%20IEEE%2011th%20International%20Conference%20on%20Healthcare%20Informatics%20(ICHI)&rft.au=Tresner-Kirsch,%20David&rft.date=2023-06-26&rft.spage=457&rft.epage=459&rft.pages=457-459&rft.eissn=2575-2634&rft.coden=IEEPAD&rft_id=info:doi/10.1109/ICHI57859.2023.00066&rft.eisbn=9798350302639&rft_dat=%3Cieee_CHZPO%3E10337283%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i119t-14847b8bf1dc5355e1d22910ca9d85732646538050f72bc4ffe2ded9d4caf82f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10337283&rfr_iscdi=true |