# Optimal Embedding Calibration for Symbolic Music Similarity

arXiv: https://arxiv.org/abs/2103.07656 · HTML: https://mlsanity.com/paper/2103.07656/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 13 Mar 2021.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [All-but-the-Top: Simple and Effective Postprocessing for Word Representations](https://mlsanity.com/paper/1702.01417/) (2017)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [An Unsupervised Sentence Embedding Method by Mutual Information Maximization](https://mlsanity.com/paper/2009.12061/) (2020)
- [On the Sentence Embeddings from Pre-trained Language Models](https://mlsanity.com/paper/2011.05864/) (2020)

## Built on by (most cited first, 1 of 1)

- [LyricSIM: A novel Dataset and Benchmark for Similarity Detection in Spanish Song LyricS](https://mlsanity.com/paper/2306.01325/) (2023)

## Abstract (arXiv)

In natural language processing (NLP), the semantic similarity task requires large-scale, high-quality human-annotated labels for fine-tuning or evaluation. By contrast, in cases of music similarity, such labels are expensive to collect and largely dependent on the annotator's artistic preferences. Recent research has demonstrated that embedding calibration technique can greatly increase semantic similarity performance of the pre-trained language model without fine-tuning. However, it is yet unknown which calibration method is the best and how much performance improvement can be achieved. To address these issues, we propose using composer information to construct labels for automatically evaluating music similarity. Under this paradigm, we discover the optimal combination of embedding calibration which achieves superior metrics than the baseline methods.