Music Playlist Title Generation: A Machine-Translation Approach

TL;DR

This paper introduces a machine-translation approach using RNN and Transformer models to generate playlist titles from music tracks, highlighting the importance of order removal techniques for improved performance.

Contribution

It adapts sequence-to-sequence models to music data and proposes novel techniques to handle the orderless nature of playlists, enhancing title generation accuracy.

Findings

Transformer models outperform RNN models.

Removing input sequence order improves performance.

Data augmentation via shuffling benefits model accuracy.

Abstract

We propose a machine-translation approach to automatically generate a playlist title from a set of music tracks. We take a sequence of track IDs as input and a sequence of words in a playlist title as output, adapting the sequence-to-sequence framework based on Recurrent Neural Network (RNN) and Transformer to the music data. Considering the orderless nature of music tracks in a playlist, we propose two techniques that remove the order of the input sequence. One is data augmentation by shuffling and the other is deleting the positional encoding. We also reorganize the existing music playlist datasets to generate phrase-level playlist titles. The result shows that the Transformer models generally outperform the RNN model. Also, removing the order of input sequence improves the performance further.