DeepAI AI Chat
Log In Sign Up

Distributed Vector Representations of Folksong Motifs

by   Aitor Arronte-Alvarez, et al.
Universidad Politécnica de Madrid
University of Hawaii

This article presents a distributed vector representation model for learning folksong motifs. A skip-gram version of word2vec with negative sampling is used to represent high quality embeddings. Motifs from the Essen Folksong collection are compared based on their cosine similarity. A new evaluation method for testing the quality of the embeddings based on a melodic similarity task is presented to show how the vector space can represent complex contextual features, and how it can be utilized for the study of folksong variation.


page 1

page 2

page 3

page 4


Issues in evaluating semantic spaces using word analogies

The offset method for solving word analogies has become a standard evalu...

CLUSE: Cross-Lingual Unsupervised Sense Embeddings

This paper proposes a modularized sense induction and representation lea...

Modeling Musical Context with Word2vec

We present a semantic vector space model for capturing complex polyphoni...

Plagiarism Detection on Electronic Text based Assignments using Vector Space Model (ICIAfS14)

Plagiarism is known as illegal use of others' part of work or whole work...

An open-source framework for ExpFinder integrating N-gram Vector Space Model and μCO-HITS

Finding experts drives successful collaborations and high-quality produc...

Build2Vec: Building Representation in Vector Space

In this paper, we represent a methodology of a graph embeddings algorith...