Filter and export

Publications

What is a Publication?
2 Publications matching the given criteria: (Clear all filters)
Author: Lukrécia Mertová2
ReStoRunT: Simple Recording, Storing, Running and Tracing changes in Spreadsheets

Abstract (Expand)

In addition to the ubiquitous big data, one key challenge indata processing and management in the life sciences is the diversity ofsmall data. Diverse pieces of small data have to be transformed … intostandards-compliant data. Here, the challenge lies not in the difficulty ofsingle steps that need to be performed, but rather in the fact that manytransformation tasks are to be performed once or only a few times. Thislimits the time that can be put into automated approaches, which inturn severely limits the verifiability of such transformations.As much of the data to be processed is stored in spreadsheets, withinthis paper we justify and propose a lightweight recording-based solutionthat works on a wide variety of spreadsheet programs, from MicrosoftExcel to Google Docs.

Authors: Wolfgang Müller, Lukrécia Mertová

Date Published: 23rd Mar 2023

Publication Type: Journal

Combining dictionary- and rule-based approximate entity linking with tuned BioBERT

Abstract (Expand)

Chemical named entity recognition (NER) is a significant step for many downstream applications like entity linking for the chemical text-mining pipeline. However, the identification of chemical entities … in a biomedical text is a challenging task due to the diverse morphology of chemical entities and the different types of chemical nomenclature. In this work, we describe our approach that was submitted for BioCreative version 7 challenge Track 2, focusing on the ‘Chemical Identification’ task for identifying chemical entities and entity linking, using MeSH. For this purpose, we have applied a two-stage approach as follows (a) usage of fine-tuned BioBERT for identification of chemical entities (b) semantic approximate search in MeSH and PubChem databases for entity linking. There was some friction between the two approaches, as our rule-based approach did not harmonise optimally with partially recognized words forwarded by the BERT component. For our future work, we aim to resolve the issue of the artefacts arising from BERT tokenizers and develop joint learning of chemical named entity recognition and entity linking using pre-trained transformer-based models and compare their performance with our preliminary approach. Next, we will improve the efficiency of our approximate search in reference databases during entity linking. This task is non-trivial as it entails determining similarity scores of large sets of trees with respect to a query tree. Ideally, this will enable flexible parametrization and rule selection for the entity linking search.

Authors: Ghadeer Mobasher, Lukrécia Mertová, Sucheta Ghosh, Olga Krebs, Bettina Heinlein, Wolfgang Müller

Date Published: 11th Nov 2021

Publication Type: Proceedings

Powered by
 (v.1.16.2)
About FAIRDOMHub | Funding and Programmes | Credits | Terms & Conditions | Imprint | Cookie preferences
Copyright © 2008 - 2024 The University of Manchester and HITS gGmbH