arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07656cs.SDcs.CLeess.AS
收藏

符号音乐相似性的最优嵌入校正

Optimal Embedding Calibration for Symbolic Music Similarity

Central Conservatory of Music(中央音乐学院);Tsinghua University(清华大学)

Xinran Zhang, Maosong Sun, Jiafeng Liu, Xiaobing Li

摘要:

在自然语言处理(NLP)中,语义相似性任务需要大规模、高质量的人工标注标签进行微调或评估。相比之下,在音乐相似性的情况下,这样的标签是昂贵的收集和很大程度上取决于注释者的艺术偏好。最近的研究表明,嵌入校准技术可以大大提高预训练的语言模型的语义相似度性能,而无需微调。然而,目前还不知道哪种校准方法是最好的,以及可以实现多大的性能改进。为了解决这些问题,我们建议使用作曲家的信息来构建标签自动评估音乐相似性。在这种模式下,我们发现嵌入校准的最佳组合,实现优于基线方法的指标。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑