Dissertation/ Thesis

Knowledge extraction and representation learning for music recommendation and classification

Bibliographic Details
Title: Knowledge extraction and representation learning for music recommendation and classification
Authors: Oramas Martín, Sergio
Contributors: University/Department: Universitat Pompeu Fabra. Departament de Tecnologies de la Informació i les Comunicacions
Thesis Advisors: Serra, Xavier
Source: TDX (Tesis Doctorals en Xarxa)
Publisher Information: Universitat Pompeu Fabra, 2017.
Publication Year: 2017
Physical Description: 177 p.
Subject Terms: Music information retrieval, Recommender systems, Natural language processing, Deep learning, Musicology, Classification, Machine learning, Representation learning, Information extraction, Música, Sistemas de recomendación, Procesado del lenguaje natural, Aprendizaje profundo, Musicología, Clasificación, Aprendizaje automático, Extracción de información
Description: In this thesis, we address the problems of classifying and recommending music present in large collections. We focus on the semantic enrichment of descriptions associated to musical items (e.g., artists biographies, album reviews, metadata), and the exploitation of multimodal data (e.g., text, audio, images). To this end, we first focus on the problem of linking music-related texts with online knowledge repositories and on the automated construction of music knowledge bases. Then, we show how modeling semantic information may impact musicological studies and helps to outperform purely text-based approaches in music similarity, classification, and recommendation. Next, we focus on learning new data representations from multimodal content using deep learning architectures, addressing the problems of cold-start music recommendation and multi-label music genre classification, combining audio, text, and images. We show how the semantic enrichment of texts and the combination of learned data representations improve the performance on both tasks.
Description (Translated): En esta tesis, abordamos los problemas de clasificar y recomendar música en grandes colecciones, centrándonos en el enriquecimiento semántico de descripciones (biografías, reseñas, metadatos), y en el aprovechamiento de datos multimodales (textos, audios e imágenes). Primero nos centramos en enlazar textos con bases de conocimiento y en su construcción automatizada. Luego mostramos cómo el modelado de información semántica puede impactar en estudios musicológicos, y contribuye a superar a métodos basados en texto, tanto en similitud como en clasificación y recomendación de música. A continuación, investigamos el aprendizaje de nuevas representaciones de datos a partir de contenidos multimodales utilizando redes neuronales, y lo aplicamos a los problemas de recomendar música nueva y clasificar géneros musicales con múltiples etiquetas, mostrando que el enriquecimiento semántico y la combinación de representaciones aprendidas produce mejores resultados.
Programa de doctorat en Tecnologies de la Informació i les Comunicacions
Document Type: Dissertation/Thesis
File Description: application/pdf
Language: English
Access URL: http://hdl.handle.net/10803/457709
Rights: L'accés als continguts d'aquesta tesi queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/4.0/
Accession Number: edstdx.10803.457709
Database: TDX
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://hdl.handle.net/10803/457709#
    Name: EDS - TDX (ns324271)
    Category: fullText
    Text: View record in TDX
Header DbId: edstdx
DbLabel: TDX
An: edstdx.10803.457709
RelevancyScore: 1319
AccessLevel: 3
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 1318.93640136719
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Knowledge extraction and representation learning for music recommendation and classification
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Oramas+Martín%2C+Sergio%22">Oramas Martín, Sergio</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: University/Department: Universitat Pompeu Fabra. Departament de Tecnologies de la Informació i les Comunicacions
– Name: Author
  Label: Thesis Advisors
  Group: Au
  Data: Serra, Xavier
– Name: TitleSource
  Label: Source
  Group: Src
  Data: TDX (Tesis Doctorals en Xarxa)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Universitat Pompeu Fabra, 2017.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2017
– Name: PhysDesc
  Label: Physical Description
  Group: PhysDesc
  Data: 177 p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Music+information+retrieval%22">Music information retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Recommender+systems%22">Recommender systems</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Musicology%22">Musicology</searchLink><br /><searchLink fieldCode="DE" term="%22Classification%22">Classification</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Representation+learning%22">Representation learning</searchLink><br /><searchLink fieldCode="DE" term="%22Information+extraction%22">Information extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Música%22">Música</searchLink><br /><searchLink fieldCode="DE" term="%22Sistemas+de+recomendación%22">Sistemas de recomendación</searchLink><br /><searchLink fieldCode="DE" term="%22Procesado+del+lenguaje+natural%22">Procesado del lenguaje natural</searchLink><br /><searchLink fieldCode="DE" term="%22Aprendizaje+profundo%22">Aprendizaje profundo</searchLink><br /><searchLink fieldCode="DE" term="%22Musicología%22">Musicología</searchLink><br /><searchLink fieldCode="DE" term="%22Clasificación%22">Clasificación</searchLink><br /><searchLink fieldCode="DE" term="%22Aprendizaje+automático%22">Aprendizaje automático</searchLink><br /><searchLink fieldCode="DE" term="%22Extracción+de+información%22">Extracción de información</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: In this thesis, we address the problems of classifying and recommending music present in large collections. We focus on the semantic enrichment of descriptions associated to musical items (e.g., artists biographies, album reviews, metadata), and the exploitation of multimodal data (e.g., text, audio, images). To this end, we first focus on the problem of linking music-related texts with online knowledge repositories and on the automated construction of music knowledge bases. Then, we show how modeling semantic information may impact musicological studies and helps to outperform purely text-based approaches in music similarity, classification, and recommendation. Next, we focus on learning new data representations from multimodal content using deep learning architectures, addressing the problems of cold-start music recommendation and multi-label music genre classification, combining audio, text, and images. We show how the semantic enrichment of texts and the combination of learned data representations improve the performance on both tasks.
– Name: Abstract
  Label: Description (Translated)
  Group: Ab
  Data: En esta tesis, abordamos los problemas de clasificar y recomendar música en grandes colecciones, centrándonos en el enriquecimiento semántico de descripciones (biografías, reseñas, metadatos), y en el aprovechamiento de datos multimodales (textos, audios e imágenes). Primero nos centramos en enlazar textos con bases de conocimiento y en su construcción automatizada. Luego mostramos cómo el modelado de información semántica puede impactar en estudios musicológicos, y contribuye a superar a métodos basados en texto, tanto en similitud como en clasificación y recomendación de música. A continuación, investigamos el aprendizaje de nuevas representaciones de datos a partir de contenidos multimodales utilizando redes neuronales, y lo aplicamos a los problemas de recomendar música nueva y clasificar géneros musicales con múltiples etiquetas, mostrando que el enriquecimiento semántico y la combinación de representaciones aprendidas produce mejores resultados.<br />Programa de doctorat en Tecnologies de la Informació i les Comunicacions
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Dissertation/Thesis
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="http://hdl.handle.net/10803/457709" linkWindow="_blank">http://hdl.handle.net/10803/457709</link>
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: L'accés als continguts d'aquesta tesi queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/4.0/
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edstdx.10803.457709
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edstdx&AN=edstdx.10803.457709
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 177
    Subjects:
      – SubjectFull: Music information retrieval
        Type: general
      – SubjectFull: Recommender systems
        Type: general
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Musicology
        Type: general
      – SubjectFull: Classification
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Representation learning
        Type: general
      – SubjectFull: Information extraction
        Type: general
      – SubjectFull: Música
        Type: general
      – SubjectFull: Sistemas de recomendación
        Type: general
      – SubjectFull: Procesado del lenguaje natural
        Type: general
      – SubjectFull: Aprendizaje profundo
        Type: general
      – SubjectFull: Musicología
        Type: general
      – SubjectFull: Clasificación
        Type: general
      – SubjectFull: Aprendizaje automático
        Type: general
      – SubjectFull: Extracción de información
        Type: general
    Titles:
      – TitleFull: Knowledge extraction and representation learning for music recommendation and classification
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Oramas Martín, Sergio
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 29
              M: 11
              Type: published
              Y: 2017
ResultId 1