Information Extraction of Music Entities in Conversational Music Queries

Simon Hachmeier, Robert Jäschke


Abstract
The detection of music entities such as songs or performing artists in natural language queries is an important task when designing conversational music recommendation agents. Previous research has observed the applicability of named entity recognition approaches for this task based on pre-trained encoders like BERT. In recent years, large language models (LLMs) have surpassed these encoders in a variety of downstream tasks. In this paper, we validate the use of LLMs for information extraction of music entities in conversational queries by few-shot prompting. We test different numbers of examples and compare two sampling methods to obtain few-shot examples. Our results indicate that LLM performance can achieve state-of-the-art performance in the task.
Anthology ID:
2024.nlp4musa-1.7
Volume:
Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA)
Month:
November
Year:
2024
Address:
Oakland, USA
Editors:
Anna Kruspe, Sergio Oramas, Elena V. Epure, Mohamed Sordo, Benno Weck, SeungHeon Doh, Minz Won, Ilaria Manco, Gabriel Meseguer-Brocal
Venues:
NLP4MusA | WS
SIG:
Publisher:
Association for Computational Lingustics
Note:
Pages:
37–42
Language:
URL:
https://aclanthology.org/2024.nlp4musa-1.7/
DOI:
Bibkey:
Cite (ACL):
Simon Hachmeier and Robert Jäschke. 2024. Information Extraction of Music Entities in Conversational Music Queries. In Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA), pages 37–42, Oakland, USA. Association for Computational Lingustics.
Cite (Informal):
Information Extraction of Music Entities in Conversational Music Queries (Hachmeier & Jäschke, NLP4MusA 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nlp4musa-1.7.pdf