White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

The Detection of Contradictory Claims in Biomedical Abstracts

Alamri, Abdulaziz (2016) The Detection of Contradictory Claims in Biomedical Abstracts. PhD thesis, University of Sheffield.

Other (PDF)
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (2083Kb) | Preview


Research claims in the biomedical domain are not always consistent, and may even be contradictory. This thesis explores contradictions between research claims in order to determine whether or not it is possible to develop a solution to automate the detection of such phenomena. Such a solution will help decision-makers, including researchers, to alleviate the effects of contradictory claims on their decisions. This study develops two methodologies to construct corpora of contradictions. The first methodology utilises systematic reviews to construct a manually-annotated corpus of contradictions. The second methodology uses a different approach to construct a corpus of contradictions which does not rely on human annotation. This methodology is proposed to overcome the limitations of the manual annotation approach. Moreover, this thesis proposes a pipeline to detect contradictions in abstracts. The pipeline takes a question and a list of research abstracts which may contain answers to it. The output of the pipeline is a list of sentences extracted from abstracts which answer the question, where each sentence is annotated with an assertion value with respect to the question. Claims which feature opposing assertion values are considered as potentially contradictory claims. The research demonstrates that automating the detection of contradictory claims in research abstracts is a feasible problem.

Item Type: Thesis (PhD)
Academic Units: The University of Sheffield > Faculty of Engineering (Sheffield) > Computer Science (Sheffield)
The University of Sheffield > Faculty of Science (Sheffield) > Computer Science (Sheffield)
Identification Number/EthosID: uk.bl.ethos.700890
Depositing User: Mr Abdulaziz Alamri
Date Deposited: 03 Jan 2017 11:54
Last Modified: 12 Oct 2018 09:31
URI: http://etheses.whiterose.ac.uk/id/eprint/15893

You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)