An approach to automatic music band member detection based on supervised learning

Authors:
Peter Knees
Affiliations:
Department of Computational Perception, Johannes Kepler University, Linz, Austria
Venue:
AMR'11 Proceedings of the 9th international conference on Adaptive Multimedia Retrieval: large-scale multimedia retrieval and evaluation
Year:
2011

Citing 11
Cited 0

Knowledge-based extraction of named entities

Proceedings of the eleventh international conference on Information and knowledge management
Automatic Ontology-Based Knowledge Extraction from Web Documents

IEEE Intelligent Systems
Nymble: a high-performance learning name-finder

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Automatic acquisition of hyponyms from large text corpora

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Unsupervised named entity classification models and their ensembles

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Extracting relations from large text collections

Extracting relations from large text collections
Automatically Detecting Members and Instrumentation of Music Bands Via Web Content Mining

Adaptive Multimedial Retrieval: Retrieval, User, and Semantics
Web-scale named entity recognition

Proceedings of the 17th ACM conference on Information and knowledge management
Adapting svm for data sparseness and imbalance: A case study in information extraction

Natural Language Engineering
Song Clustering Using Peer-to-Peer Co-occurrences

ISM '09 Proceedings of the 2009 11th IEEE International Symposium on Multimedia
SVM based learning system for information extraction

Proceedings of the First international conference on Deterministic and Statistical Methods in Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatically extracting factual information about musical entities, such as detecting the members of a band, helps building advanced browsing interfaces and recommendation systems. In this paper, a supervised approach to learning to identify and to extract the members of a music band from related Web documents is proposed. While existing methods utilize manually optimized rules for this purpose, the presented technique learns from automatically labelled examples, making therefore also manual annotation obsolete. The presented approach is compared against existing rule-based methods for band-member extraction by performing systematic evaluation on two different test sets.