Predicting User Intents and Musical Attributes from Music Discovery Conversations

Intent classification is a text understanding task that identifies user needs from input text queries. While intent classification has been extensively studied in various domains, it has not received much attention in the music domain. In this paper, we investigate intent classification models for m...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Kwon, Daeyong, Doh, SeungHeon, Nam, Juhan
Format: Article
Language:English
Subjects:
Classification
Music
Queries
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Kwon, Daeyong
Doh, SeungHeon
Nam, Juhan
description Intent classification is a text understanding task that identifies user needs from input text queries. While intent classification has been extensively studied in various domains, it has not received much attention in the music domain. In this paper, we investigate intent classification models for music discovery conversation, focusing on pre-trained language models. Rather than only predicting functional needs: intent classification, we also include a task for classifying musical needs: musical attribute classification. Additionally, we propose a method of concatenating previous chat history with just single-turn user queries in the input text, allowing the model to understand the overall conversation context better. Our proposed model significantly improves the F1 score for both user intent and musical attribute classification, and surpasses the zero-shot and few-shot performance of the pretrained Llama 3 model.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3131614086</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3131614086</sourcerecordid><originalsourceid>FETCH-proquest_journals_31316140863</originalsourceid><addsrcrecordid>eNqNikEKwjAQAIMgWLR_WPBcaJK29ipV0YOgoOcS21RSaqLZjeDvFfQBngZmZsQiISVPykyICYsR-zRNRbEQeS4jdjx43ZqGjL3CGbWHnSVtCUHZFvYBTaMGWBJ5cwmkETrvbl8PK4ONe2r_gsrZD1GRcRZnbNypAXX845TNN-tTtU3u3j2CRqp7F7z9pFpyyQuepWUh_7ve2QQ_yA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3131614086</pqid></control><display><type>article</type><title>Predicting User Intents and Musical Attributes from Music Discovery Conversations</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Kwon, Daeyong ; Doh, SeungHeon ; Nam, Juhan</creator><creatorcontrib>Kwon, Daeyong ; Doh, SeungHeon ; Nam, Juhan</creatorcontrib><description>Intent classification is a text understanding task that identifies user needs from input text queries. While intent classification has been extensively studied in various domains, it has not received much attention in the music domain. In this paper, we investigate intent classification models for music discovery conversation, focusing on pre-trained language models. Rather than only predicting functional needs: intent classification, we also include a task for classifying musical needs: musical attribute classification. Additionally, we propose a method of concatenating previous chat history with just single-turn user queries in the input text, allowing the model to understand the overall conversation context better. Our proposed model significantly improves the F1 score for both user intent and musical attribute classification, and surpasses the zero-shot and few-shot performance of the pretrained Llama 3 model.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Classification ; Music ; Queries</subject><ispartof>arXiv.org, 2024-11</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3131614086?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25731,36989,44566</link.rule.ids></links><search><creatorcontrib>Kwon, Daeyong</creatorcontrib><creatorcontrib>Doh, SeungHeon</creatorcontrib><creatorcontrib>Nam, Juhan</creatorcontrib><title>Predicting User Intents and Musical Attributes from Music Discovery Conversations</title><title>arXiv.org</title><description>Intent classification is a text understanding task that identifies user needs from input text queries. While intent classification has been extensively studied in various domains, it has not received much attention in the music domain. In this paper, we investigate intent classification models for music discovery conversation, focusing on pre-trained language models. Rather than only predicting functional needs: intent classification, we also include a task for classifying musical needs: musical attribute classification. Additionally, we propose a method of concatenating previous chat history with just single-turn user queries in the input text, allowing the model to understand the overall conversation context better. Our proposed model significantly improves the F1 score for both user intent and musical attribute classification, and surpasses the zero-shot and few-shot performance of the pretrained Llama 3 model.</description><subject>Classification</subject><subject>Music</subject><subject>Queries</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNikEKwjAQAIMgWLR_WPBcaJK29ipV0YOgoOcS21RSaqLZjeDvFfQBngZmZsQiISVPykyICYsR-zRNRbEQeS4jdjx43ZqGjL3CGbWHnSVtCUHZFvYBTaMGWBJ5cwmkETrvbl8PK4ONe2r_gsrZD1GRcRZnbNypAXX845TNN-tTtU3u3j2CRqp7F7z9pFpyyQuepWUh_7ve2QQ_yA</recordid><startdate>20241120</startdate><enddate>20241120</enddate><creator>Kwon, Daeyong</creator><creator>Doh, SeungHeon</creator><creator>Nam, Juhan</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241120</creationdate><title>Predicting User Intents and Musical Attributes from Music Discovery Conversations</title><author>Kwon, Daeyong ; Doh, SeungHeon ; Nam, Juhan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31316140863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Classification</topic><topic>Music</topic><topic>Queries</topic><toplevel>online_resources</toplevel><creatorcontrib>Kwon, Daeyong</creatorcontrib><creatorcontrib>Doh, SeungHeon</creatorcontrib><creatorcontrib>Nam, Juhan</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kwon, Daeyong</au><au>Doh, SeungHeon</au><au>Nam, Juhan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Predicting User Intents and Musical Attributes from Music Discovery Conversations</atitle><jtitle>arXiv.org</jtitle><date>2024-11-20</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Intent classification is a text understanding task that identifies user needs from input text queries. While intent classification has been extensively studied in various domains, it has not received much attention in the music domain. In this paper, we investigate intent classification models for music discovery conversation, focusing on pre-trained language models. Rather than only predicting functional needs: intent classification, we also include a task for classifying musical needs: musical attribute classification. Additionally, we propose a method of concatenating previous chat history with just single-turn user queries in the input text, allowing the model to understand the overall conversation context better. Our proposed model significantly improves the F1 score for both user intent and musical attribute classification, and surpasses the zero-shot and few-shot performance of the pretrained Llama 3 model.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_3131614086
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Classification
Music
Queries
title Predicting User Intents and Musical Attributes from Music Discovery Conversations
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T14%3A06%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Predicting%20User%20Intents%20and%20Musical%20Attributes%20from%20Music%20Discovery%20Conversations&rft.jtitle=arXiv.org&rft.au=Kwon,%20Daeyong&rft.date=2024-11-20&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3131614086%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31316140863%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3131614086&rft_id=info:pmid/&rfr_iscdi=true