Music Playlist Title Generation Using Artist Information
This work addresses the need for better playlist title generation in music streaming services to attract users and aid music discovery, but it is incremental as it builds on existing encoder-decoder models with modifications for input representation and data splitting.
The paper tackles the problem of automatically generating music playlist titles from a set of tracks by proposing an encoder-decoder model that uses artist IDs instead of track IDs to address long-tail distribution issues and introduces a chronological data split for handling newly-released tracks. The result shows that the artist-based approach significantly enhances performance in word overlap, semantic relevance, and diversity compared to track-based methods.
Automatically generating or captioning music playlist titles given a set of tracks is of significant interest in music streaming services as customized playlists are widely used in personalized music recommendation, and well-composed text titles attract users and help their music discovery. We present an encoder-decoder model that generates a playlist title from a sequence of music tracks. While previous work takes track IDs as tokenized input for playlist title generation, we use artist IDs corresponding to the tracks to mitigate the issue from the long-tail distribution of tracks included in the playlist dataset. Also, we introduce a chronological data split method to deal with newly-released tracks in real-world scenarios. Comparing the track IDs and artist IDs as input sequences, we show that the artist-based approach significantly enhances the performance in terms of word overlap, semantic relevance, and diversity.