• Publications
  • Influence
NaCTeM-UoM @ CL-SciSumm 2019
TLDR
The National Centre for Text Mining University of Manchester systems submitted in CL-SciSumm 2019 Shared Task at BIRNDL 2019 Workshop are introduced and supervised and semi-supervised approaches are looked into and the potential of adapting bidirectional transformers for each task is explored. Expand
Using uncertainty to link and rank evidence from biomedical literature for model curation
TLDR
A novel method for extracting uncertainty from the literature using a hybrid approach that combines rule induction and machine learning is presented, using subjective logic theory to combine multiple uncertainty values extracted from different sources for the same interaction. Expand
A Text Mining-Based Framework for Constructing an RDF-Compliant Biodiversity Knowledge Repository
TLDR
A text mining-based framework for automatically transforming text into a structured knowledge repository that facilitates knowledge discovery over a huge amount of biodiversity literature by retrieving annotations matching user-specified queries is developed. Expand
Evaluation of brain perfusion in specific Brodmann areas in Frontotemporal dementia and Alzheimer disease using automated 3-D voxel based analysis
Introduction. Brain perfusion studies with single-photon emission computed tomography (SPECT) have been applied in demented patients to provide better discrimination between frontotemporal dementiaExpand
Construction of a Biodiversity Knowledge Repository using a Text Mining-based Framework
TLDR
A text mining-based framework for automatically transforming text into a structured knowledge repository, accessible as a SPARQL endpoint, that supports knowledge discovery over a huge amount of biodiversity literature by retrieving annotations matching user-specified queries. Expand
Cited text span identification for scientific summarisation using pre-trained encoders
TLDR
It is shown that identifying and fine-tuning the language models on unlabelled or augmented domain specific data can improve the performance of cited text span identification models. Expand
Semantic Enrichment of Pretrained Embedding Output for Unsupervised IR
TLDR
This paper investigates the potential of semantically enhancing deep transformer architectures using SNOMED-CT in order to answer user queries in an unsupervised manner and presents the approach for adapting such an approach to full papers, such as kaggle's CORD-19 full-text dataset challenge. Expand
Paths for uncertainty: Exploring the intricacies of uncertainty identification for news
TLDR
The different aspects that affect the certainty of an extracted event in a news article are delve into and whether they can be easily identified by techniques already validated in the biomedical domain are examined. Expand
LitPathExplorer: a confidence‐based visual text analytics tool for exploring literature‐enriched pathway models
TLDR
LitPathExplorer is a visual text analytics tool that integrates advanced text mining, semi‐supervised learning and interactive visualization, to facilitate the exploration and analysis of pathway models using statements extracted automatically from the literature and organized according to levels of confidence. Expand
...
1
2
...