no code implementations • insights (ACL) 2022 • Goonmeet Bajaj, Vinh Nguyen, Thilini Wijesiriwardene, Hong Yung Yip, Vishesh Javangula, Amit Sheth, Srinivasan Parthasarathy, Olivier Bodenreider
Recent work uses a Siamese Network, initialized with BioWordVec embeddings (distributed word embeddings), for predicting synonymy among biomedical terms to automate a part of the UMLS (Unified Medical Language System) Metathesaurus construction process.
1 code implementation • 25 Nov 2023 • Bernal Jimenez Gutierrez, Yuqing Mao, Vinh Nguyen, Kin Wah Fung, Yu Su, Olivier Bodenreider
In this work, we study the case of UMLS vocabulary insertion, an important real-world task in which hundreds of thousands of new terms, referred to as atoms, are added to the UMLS, one of the most comprehensive open-source biomedical knowledge bases.
no code implementations • 6 Nov 2023 • Tuan Nguyen, Hirotada Honda, Takashi Sano, Vinh Nguyen, Shugo Nakamura, Tan M. Nguyen
We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoothing phenomenon, in which node features in GNNs become indistinguishable as the number of layers increases.
no code implementations • 6 Nov 2023 • Tuan Nguyen, Tam Nguyen, Vinh Nguyen, Tan M. Nguyen
$p$-Laplacian regularization, rooted in graph and image signal processing, introduces a parameter $p$ to control the regularization effect on these data.
1 code implementation • 28 Nov 2022 • Khang Nguyen, Hieu Nong, Vinh Nguyen, Nhat Ho, Stanley Osher, Tan Nguyen
Graph Neural Networks (GNNs) had been demonstrated to be inherently susceptible to the problems of over-smoothing and over-squashing.
1 code implementation • 8 Jul 2022 • Chuong H. Nguyen, Su Huynh, Vinh Nguyen, Ngoc Nguyen
Since being introduced in 2020, Vision Transformers (ViT) has been steadily breaking the record for many vision tasks and are often described as ``all-you-need" to replace ConvNet.
no code implementations • 21 May 2022 • Vinh Nguyen, Olivier Bodenreider
In this paper, we present a set of reusable and reproducible resources including (1) a dataset generator, (2) three datasets generated by using the generator, and (3) three baseline approaches.
1 code implementation • 27 Apr 2022 • Thilini Wijesiriwardene, Vinh Nguyen, Goonmeet Bajaj, Hong Yung Yip, Vishesh Javangula, Yuqing Mao, Kin Wah Fung, Srinivasan Parthasarathy, Amit P. Sheth, Olivier Bodenreider
The effectiveness of UBERT for UMLS Metathesaurus construction process is evaluated using the UMLS Vocabulary Alignment (UVA) task.
no code implementations • 14 Sep 2021 • Goonmeet Bajaj, Vinh Nguyen, Thilini Wijesiriwardene, Hong Yung Yip, Vishesh Javangula, Srinivasan Parthasarathy, Amit Sheth, Olivier Bodenreider
Given the SOTA performance of these BERT models for other downstream tasks, our experiments yield surprisingly interesting results: (1) in both model architectures, the approaches employing these biomedical BERT-based models do not outperform the existing approaches using Siamese Network with BioWordVec embeddings for the UMLS synonymy prediction task, (2) the original BioBERT large model that has not been pre-trained with the UMLS outperforms the SapBERT models that have been pre-trained with the UMLS, and (3) using the Siamese Networks yields better performance for synonymy prediction when compared to using the biomedical BERT models.
no code implementations • 27 Jul 2019 • Oscar Correa, Jeffrey Chan, Vinh Nguyen
Secondly, blockmodelling is a summary representation of a network which regards not only membership of nodes but also relations between clusters.
no code implementations • 20 Jan 2017 • Vinh Nguyen, Amit Sheth
This formal semantics also allows us to derive a new set of entailment rules that could entail new contextual triples about triples.
no code implementations • 15 Sep 2015 • Vinh Nguyen, Olivier Bodenreider, Krishnaprasad Thirunarayan, Gang Fu, Evan Bolton, Núria Queralt Rosinach, Laura I. Furlong, Michel Dumontier, Amit Sheth
If the singleton property triples describe a data triple, then how can a reasoner infer this data triple from the singleton property triples?