Search

Your search keyword '"Verspoor, Karin"' showing total 8 results
Start Over Author "Verspoor, Karin" Search Limiters Full Text Publication Year Range This year
8 results on '"Verspoor, Karin"'

1. Graph Transformers: A Survey

Author

Shehzad, Ahsan, Xia, Feng, Abid, Shagufta, Peng, Ciyuan, Yu, Shuo, Zhang, Dongyu, and Verspoor, Karin

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, 68T07, 68T05, 68U01, I.2.6
Abstract

Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility across various graph-related tasks. This survey provides an in-depth review of recent progress and challenges in graph transformer research. We begin with foundational concepts of graphs and transformers. We then explore design perspectives of graph transformers, focusing on how they integrate graph inductive biases and graph attention mechanisms into the transformer architecture. Furthermore, we propose a taxonomy classifying graph transformers based on depth, scalability, and pre-training strategies, summarizing key principles for effective development of graph transformer models. Beyond technical analysis, we discuss the applications of graph transformer models for node-level, edge-level, and graph-level tasks, exploring their potential in other application scenarios as well. Finally, we identify remaining challenges in the field, such as scalability and efficiency, generalization and robustness, interpretability and explainability, dynamic and complex graphs, as well as data quality and diversity, charting future directions for graph transformer research., Comment: 23 pages, 4 figures

Published
2024

2. Revisiting subword tokenization: A case study on affixal negation in large language models

Author

Truong, Thinh Hung, Otmakhova, Yulia, Verspoor, Karin, Cohn, Trevor, and Baldwin, Timothy

Subjects
Computer Science - Computation and Language
Abstract

In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their tokenizers are often not morphologically plausible. We conduct extensive experiments using LLMs with different subword tokenization methods, which lead to several insights on the interaction between tokenization performance and negation sensitivity. Despite some interesting mismatches between tokenization accuracy and negation detection performance, we show that models can, on the whole, reliably recognize the meaning of affixal negation., Comment: NAACL 2024

Published
2024

3. Deep Outdated Fact Detection in Knowledge Graphs

Author

Tu, Huiling, Yu, Shuo, Saikrishna, Vidya, Xia, Feng, and Verspoor, Karin

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Digital Libraries, Computer Science - Machine Learning, 68T09, 68T30, 68P20, I.2.6, I.2.4, H.3.7, H.3.3
Abstract

Knowledge graphs (KGs) have garnered significant attention for their vast potential across diverse domains. However, the issue of outdated facts poses a challenge to KGs, affecting their overall quality as real-world information evolves. Existing solutions for outdated fact detection often rely on manual recognition. In response, this paper presents DEAN (Deep outdatEd fAct detectioN), a novel deep learning-based framework designed to identify outdated facts within KGs. DEAN distinguishes itself by capturing implicit structural information among facts through comprehensive modeling of both entities and relations. To effectively uncover latent out-of-date information, DEAN employs a contrastive approach based on a pre-defined Relations-to-Nodes (R2N) graph, weighted by the number of entities. Experimental results demonstrate the effectiveness and superiority of DEAN over state-of-the-art baseline methods., Comment: 10 pages, 6 figures

Published
2024
Full Text
View/download PDF

4. Integration of polygenic and gut metagenomic risk prediction for common diseases.

Author

Liu, Yang, Ritchie, Scott, Teo, Shu, Ruuskanen, Matti, Kambur, Oleg, Zhu, Qiyun, Sanders, Jon, Vázquez-Baeza, Yoshiki, Verspoor, Karin, Jousilahti, Pekka, Lahti, Leo, Niiranen, Teemu, Salomaa, Veikko, Havulinna, Aki, Méric, Guillaume, Inouye, Michael, and Knight, Rob

Subjects
Male, Humans, Diabetes Mellitus, Type 2, Prospective Studies, Risk Factors, Coronary Artery Disease, Prostatic Neoplasms, Genetic Risk Score
Abstract

Multiomics has shown promise in noninvasive risk profiling and early detection of various common diseases. In the present study, in a prospective population-based cohort with ~18 years of e-health record follow-up, we investigated the incremental and combined value of genomic and gut metagenomic risk assessment compared with conventional risk factors for predicting incident coronary artery disease (CAD), type 2 diabetes (T2D), Alzheimer disease and prostate cancer. We found that polygenic risk scores (PRSs) improved prediction over conventional risk factors for all diseases. Gut microbiome scores improved predictive capacity over baseline age for CAD, T2D and prostate cancer. Integrated risk models of PRSs, gut microbiome scores and conventional risk factors achieved the highest predictive performance for all diseases studied compared with models based on conventional risk factors alone. The present study demonstrates that integrated PRSs and gut metagenomic risk models improve the predictive value over conventional risk factors for common chronic diseases.

Published
2024

7. Focused Contrastive Loss for Classification With Pre-Trained Language Models

Author

He, Jiayuan, Li, Yuan, Zhai, Zenan, Fang, Biaoyan, Thorne, Camilo, Druckenbrodt, Christian, Akhondi, Saber, and Verspoor, Karin

Abstract

Contrastive learning, which learns data representations by contrasting similar and dissimilar instances, has achieved great success in various domains including natural language processing (NLP). Recently, it has been demonstrated that incorporating class labels into contrastive learning, i.e., supervised contrastive learning (SCL), can further enhance the quality of the learned data representations. Although several works have shown empirically that incorporating SCL into classification models leads to better performance, the mechanism of how SCL works for classification is less studied. In this paper, we first investigate how SCL facilitates the classifier learning, where we show that the contrastive region, i.e., the data instances involved in each contrasting operation, has a crucial link to the mechanism of SCL. We reveal that the vanilla SCL is suboptimal since its behavior can be altered by variances in class distributions. Based on this finding, we propose a Focused Contrastive Loss (FoCL) for classification. Compared with SCL, FoCL defines a finer contrastive region, focusing on the data instances surrounding decision boundaries. We conduct extensive experiments on three NLP tasks: text classification, named entity recognition, and relation extraction. Experimental results show consistent and significant improvements of FoCL over strong baselines on various benchmark datasets, especially in few-shot scenarios.

Published
2024
Full Text
View/download PDF

8. Integration of background knowledge for automatic detection of inconsistencies in gene ontology annotation.

Author

Chen J, Goudey B, Geard N, and Verspoor K

Subjects
Databases, Genetic, Computational Biology methods, Semantics, Humans, Gene Ontology, Molecular Sequence Annotation methods
Abstract

Motivation: Biological background knowledge plays an important role in the manual quality assurance (QA) of biological database records. One such QA task is the detection of inconsistencies in literature-based Gene Ontology Annotation (GOA). This manual verification ensures the accuracy of the GO annotations based on a comprehensive review of the literature used as evidence, Gene Ontology (GO) terms, and annotated genes in GOA records. While automatic approaches for the detection of semantic inconsistencies in GOA have been developed, they operate within predetermined contexts, lacking the ability to leverage broader evidence, especially relevant domain-specific background knowledge. This paper investigates various types of background knowledge that could improve the detection of prevalent inconsistencies in GOA. In addition, the paper proposes several approaches to integrate background knowledge into the automatic GOA inconsistency detection process., Results: We have extended a previously developed GOA inconsistency dataset with several kinds of GOA-related background knowledge, including GeneRIF statements, biological concepts mentioned within evidence texts, GO hierarchy and existing GO annotations of the specific gene. We have proposed several effective approaches to integrate background knowledge as part of the automatic GOA inconsistency detection process. The proposed approaches can improve automatic detection of self-consistency and several of the most prevalent types of inconsistencies., This is the first study to explore the advantages of utilizing background knowledge and to propose a practical approach to incorporate knowledge in automatic GOA inconsistency detection. We establish a new benchmark for performance on this task. Our methods may be applicable to various tasks that involve incorporating biological background knowledge., Availability and Implementation: https://github.com/jiyuc/de-inconsistency., (© The Author(s) 2024. Published by Oxford University Press.)

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results