arXiv subjects

Kevin Y. Yip

Publications and source records attributed to Kevin Y. Yip.

3 recordsLinked to original sources

arXiv2026

Towards Practical Automatic Piano Reduction using BERT with Semi-supervised Learning

In this study, we present a novel automatic piano reduction method with semi-supervised machine learning. Piano reduction is an important music transformation process, which helps musicians and composers as a musical sketch for performances and analysis. The automation of such is a highly challenging research problem but could bring huge conveniences as manually doing a piano reduction takes a lot of time and effort. While supervised machine learning is often a useful tool for learning input-output mappings, it is difficult to obtain a large quantity of labelled data. We aim to solve this problem by utilizing semi-supervised learning, so that the abundant available data in classical music can be leveraged to perform the task with little or no labelling effort. In this regard, we formulate a two-step approach of music simplification followed by harmonization. We further propose and implement two possible solutions making use of an existing machine learning framework -- MidiBERT. We show that our solutions can output practical and realistic samples with an accurate reduction that needs only small adjustments in post-processing. Our study forms the groundwork for the use of semi-supervised learning in automatic piano reduction, where future researchers can take reference to produce more state-of-the-art results.

cs.SD↗

arXiv2025

Driving Accurate Allergen Prediction with Protein Language Models and Generalization-Focused Evaluation

Allergens, typically proteins capable of triggering adverse immune responses, represent a significant public health challenge. To accurately identify allergen proteins, we introduce Applm (Allergen Prediction with Protein Language Models), a computational framework that leverages the 100-billion parameter xTrimoPGLM protein language model. We show that Applm consistently outperforms seven state-of-the-art methods in a diverse set of tasks that closely resemble difficult real-world scenarios. These include identifying novel allergens that lack similar examples in the training set, differentiating between allergens and non-allergens among homologs with high sequence similarity, and assessing functional consequences of mutations that create few changes to the protein sequences. Our analysis confirms that xTrimoPGLM, originally trained on one trillion tokens to capture general protein sequence characteristics, is crucial for Applm's performance by detecting important differences among protein sequences. In addition to providing Applm as open-source software, we also provide our carefully curated benchmark datasets to facilitate future research.

cs.LG↗

arXiv2007

Comparing Classical Pathways and Modern Networks: Towards the Development of an Edge Ontology

Pathways are integral to systems biology. Their classical representation has proven useful but is inconsistent in the meaning assigned to each arrow (or edge) and inadvertently implies the isolation of one pathway from another. Conversely, modern high-throughput experiments give rise to standardized networks facilitating topological calculations. Combining these perspectives, we can embed classical pathways within large-scale networks and thus demonstrate the crosstalk between them. As more diverse types of high-throughput data become available, we can effectively merge both perspectives, embedding pathways simultaneously in multiple networks. However, the original problem still remains - the current edge representation is inadequate to accurately convey all the information in pathways. Therefore, we suggest that a standardized, well-defined, edge ontology is necessary and propose a prototype here, as a starting point for reaching this goal.

q-bio.MN↗