A5064525301- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems
- Semantic Web and Ontologies
- Research Data Management Practices
- Biomedical Text Mining and Ontologies
- Bioinformatics and Genomic Networks
- Genetics, Bioinformatics, and Biomedical Research
- Scientific Computing and Data Management
- Multimedia Communication and Technology
- Advanced Text Analysis Techniques
- Business Process Modeling and Analysis
- Data Quality and Management
- Artificial Intelligence in Games
- Computational Drug Discovery Methods
- Service-Oriented Architecture and Web Services
- Biomedical and Engineering Education
- Usability and User Interface Design
- Data Visualization and Analytics
- Science, Research, and Medicine
- Text Readability and Simplification
- Protein Degradation and Inhibitors
- Syntax, Semantics, Linguistic Variation
- Digital Accessibility for Disabilities
- Multi-Agent Systems and Negotiation
European Bioinformatics Institute
2016-2019
Open Targets
2016-2018
Trinity College Dublin
2009-2012
University of Edinburgh
2002-2008
University of Cambridge
2006-2008
King's College Hospital
2008
Colchester Hospital
2008
University of Wolverhampton
2006
We have designed and developed a data integration visualization platform that provides evidence about the association of known potential drug targets with diseases. The is to support identification prioritization biological for follow-up. Each target linked disease using integrated genome-wide from broad range sources. either target-centric workflow identify diseases may be associated specific target, or disease-centric disease. Users can easily transition between these target- workflows....
The Open Targets Platform integrates evidence from genetics, genomics, transcriptomics, drugs, animal models and scientific literature to score rank target-disease associations for drug target identification. are displayed in an intuitive user interface (https://www.targetvalidation.org), available through a REST-API (https://api.opentargets.io/v3/platform/docs/swagger-ui) bulk download (https://www.targetvalidation.org/downloads/data). In addition associations, we also aggregate display...
This paper describes a novel computer-aided procedure for generating multiple-choice test items from electronic documents. In addition to employing various Natural Language Processing techniques, including shallow parsing, automatic term extraction, sentence transformation and computing of semantic distance, the system makes use language resources such as corpora ontologies. It identifies important concepts in text generates questions about these well distractors, offering user option...
We report the results of a pilot study on generating Multiple-Choice Test Items from medical text and discuss main tasks involved in this process how our system was evaluated by domain experts.
Abstract Background Despite increasing interest in applying Natural Language Processing (NLP) to biomedical text, whether this technology can facilitate tasks such as database curation remains unclear. Results PaperBrowser is the first NLP-powered interface that was developed under a user-centered approach improve way which FlyBase curators navigate an article. In paper, we discuss how observing at work informed design and evaluation of PaperBrowser. Then, present appraise PaperBrowser's...
In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness such for information ordering in automatic text generation. We estimate empirically which is most promising metric how useful a general methodology applied on corpora. Our main result that simplest (which relies exclusively NOCB transitions) sets robust baseline cannot be outperformed by other make use additional centering-based features. This can used development both...
We present the first algorithm that computes optimal orderings of sentences into a locally coherent discourse. The runs very efficiently on variety coherence measures from literature. also show discourse ordering problem is NP-complete and cannot be approximated.
We use a reliably annotated corpus to compare metrics of coherence based on Centering Theory with respect their potential usefulness for text structuring in natural language generation. Previous corpus-based evaluations the according did not chosen structure that possible alternatives. A methodology is presented which distinguishes between Centering-based taking these alternatives into account, and represents therefore more appropriate way evaluate from perspective.
The content selection component of a natural language generation system decides which information should be communicated in its output. We use from reports on the game cricket. first describe simple factoid-to-text alignment algorithm then treat as collective classification problem and demonstrate that 'grouping' statistics at various levels granularity yields substantially improved results over probabilistic baseline. additionally show holding back specific types input data, linking...
Language Technology (LT) based applications become more popular as technology improves. Prototyping early in the design process is critical for development of high quality applications. It difficult, however, to do low-fidelity prototyping (e.g. paper prototyping) on LT. One technique that has been used this kind Wizard Oz (WOZ). However, generally involves one-off user and wizard interfaces. A tool facilitates flexible integration LT components into WOZ experiments desirable. In we explore...
We discuss how we designed the Open Targets Platform (www.targetvalidation.org), an intuitive application for bench scientists working in early drug discovery. To meet needs of our users, applied lean user experience (UX) design methods: started engaging with users very and carried out research, evaluation activities within iterative development process. also emphasize collaborative nature applying UX design, which believe is a foundation success this many other scientific projects.
This paper builds on recent research investigating sentence ordering in text production by evaluating the Centering-based metrics of coherence employed Karamanis et al. (2004) using data Barzilay and Lapata (2005). is first time that Centering evaluated empirically as a constraint several domains, verifying results reported
<ns4:p><ns4:bold>Background:</ns4:bold> Manual curation is a cornerstone of public biological data resources. However, it time-consuming process that urgently needs supportive technical solutions in the face rapid growth. Supporting scalable part mission Elixir Data Platform. Thus far, we have established infrastructure capable ingesting and aggregating text-mined outputs from multiple providers making these available via an API. This API used by Europe PMC to display specific entities...
We examine the relationship between HCI and Natural Language Processing (NLP) by performing a bibliometric analysis looking at specific example of BioNLP. identify opportunities for to fertilise current NLP research suggest that will benefit from advances in more closely.