Using Workflows to Explore and Optimise Named Entity Recognition for Chemistry

Kolluru, BalaKrishna; Hawizy, Lezan; Murray‐Rust, Peter; Tsujii, Jun’ichi; Ananiadou, Sophia

doi:10.1371/journal.pone.0020181

Cited by 22 publications

(26 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Functional status and well being were assessed using the standard form of the SF-36v2™ health survey [11]. The SF-36 has been used in patients with ME/CFS in different settings [12-25].…”

Section: Methodsmentioning

confidence: 99%

The functional status and well being of people with myalgic encephalomyelitis/chronic fatigue syndrome and their carers

et al. 2011

View full text Add to dashboard Cite

BackgroundDiagnosis of myalgic encephalomyelitis/chronic fatigue syndrome or ME/CFS is largely based on clinical history, and exclusion of identifiable causes of chronic fatigue. Characterization of cases and the impact of interventions have been limited due to clinical heterogeneity and a lack of reliable biomarkers for diagnosis and outcome measures. People with ME/CFS (PWME) often report high levels of disability, which are difficult to measure objectively. The well being of family members and those who care for PWME are also likely to be affected. This study aimed to investigate the functional status and well being of PWME and their lay carers, and to compare them with people with other chronic conditions.MethodsWe used a cross sectional design to study 170 people aged between 18 and 64 years with well characterized ME/CFS, and 44 carers, using SF-36 v2™. Mean physical and mental domains scores (scales and component summaries) were calculated and compared internally and externally with reference standards for the general population and for population groups with 10 chronic diseases.ResultsSF-36 scores in PWME were significantly reduced, especially within the physical domain (mean norm-based Physical Component Summary (PCS) score = 26.8), but also within the mental domain (mean norm-based score for Mental Component Summary (MCS) = 34.1). The lowest and highest scale scores were for "Role-Physical" (mean = 25.4) and "Mental Health" (mean = 36.7) respectively. All scores were in general lower than those for the general population and diseased-specific norms for other diseases. Carers of those with ME/CFS tended to have low scores in relation to population norms, particularly within the mental domain (mean = 45.4).ConclusionsME/CFS is disabling and has a greater impact on functional status and well being than other chronic diseases such as cancer. The emotional burden of ME/CFS is felt by lay carers as well as by people with ME/CFS. We suggest the use of generic instruments such as SF-36, in combination of other objective outcome measurements, to describe patients and assess treatments.

show abstract

“…Functional status and well being were assessed using the standard form of the SF-36v2™ health survey [11]. The SF-36 has been used in patients with ME/CFS in different settings [12-25].…”

Section: Methodsmentioning

confidence: 99%

The functional status and well being of people with myalgic encephalomyelitis/chronic fatigue syndrome and their carers

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Includes several models to choose from.Chemical Entity RecogniserA named entity recognizer optimized for chemical text (15). Includes several models to choose from.OscarMERA refactored version (16) of OSCAR 3 (17), which recognizes chemical concepts (e.g. compounds, reactions) using a maximum entropy modelSpecies TaggerA tagger for species names based on a dictionary look-up method (18)CTD LinkerNormalizes an action term to one of the types in the CTD interaction types ontology.ChEBI LinkerNormalizes a chemical compound name to an entry in the Chemical Entities of Biological Interest (ChEBI) database.UniProt LinkerNormalizes a name of a gene or gene product to a UniProt entry.EventMineA machine learning-based event extractor with models for GENIA, epigenetics, infectious diseases, pathway and cancer genetics event types (19–21)

a http://nersuite.nlplab.org

…”

Section: Componentsmentioning

confidence: 99%

Text-mining-assisted biocuration workflows in Argo

et al. 2014

Self Cite

View full text Add to dashboard Cite

Biocuration activities have been broadly categorized into the selection of relevant documents, the annotation of biological concepts of interest and identification of interactions between the concepts. Text mining has been shown to have a potential to significantly reduce the effort of biocurators in all the three activities, and various semi-automatic methodologies have been integrated into curation pipelines to support them. We investigate the suitability of Argo, a workbench for building text-mining solutions with the use of a rich graphical user interface, for the process of biocuration. Central to Argo are customizable workflows that users compose by arranging available elementary analytics to form task-specific processing units. A built-in manual annotation editor is the single most used biocuration tool of the workbench, as it allows users to create annotations directly in text, as well as modify or delete annotations created by automatic processing components. Apart from syntactic and semantic analytics, the ever-growing library of components includes several data readers and consumers that support well-established as well as emerging data interchange formats such as XMI, RDF and BioC, which facilitate the interoperability of Argo with other platforms or resources. To validate the suitability of Argo for curation activities, we participated in the BioCreative IV challenge whose purpose was to evaluate Web-based systems addressing user-defined biocuration tasks. Argo proved to have the edge over other systems in terms of flexibility of defining biocuration tasks. As expected, the versatility of the workbench inevitably lengthened the time the curators spent on learning the system before taking on the task, which may have affected the usability of Argo. The participation in the challenge gave us an opportunity to gather valuable feedback and identify areas of improvement, some of which have already been introduced.Database URL: http://argo.nactem.ac.uk

show abstract

“…Brill tagger is developed for general language POS tagging purposes, and changing it with specialized POS tagger might improve the results. It is beneficial to study the impact of each component of the system (POS tagger, the chemical named entity recognizer, or the machine learning system) on the overall performance (Kolluru et al, 2011) …”

Section: Conclusion and Future Developmentmentioning

confidence: 99%

Automatic Annotation of Parameters from Nanodevice Development Research Papers

Dieb¹,

Yoshioka²,

Hara³

et al. 2014

Proceedings of the 4th International Workshop on Computational Terminology (Computerm)

View full text Add to dashboard Cite

In utilizing nanodevice development research papers to assist in experimental planning and design, it is useful to identify and annotate characteristic categories of information contained in those papers such as source material, evaluation parameter, etc. In order to support this annotation process, we have been working to construct a nanodevice development corpus and a complementary automatic annotation scheme. Due to the variations of terms, however, recall of the automatic annotation in some information categories was not adequate. In this paper, we propose to use a basic physical quantities list to extract parameter information. We confirmed the efficiency of this method to improve the annotation of parameters. Recall for parameters increases between 4% and 7% depending on the type of parameter and analysis metric.

show abstract

Using Workflows to Explore and Optimise Named Entity Recognition for Chemistry

Cited by 22 publications

References 27 publications

The functional status and well being of people with myalgic encephalomyelitis/chronic fatigue syndrome and their carers

The functional status and well being of people with myalgic encephalomyelitis/chronic fatigue syndrome and their carers

Text-mining-assisted biocuration workflows in Argo

Automatic Annotation of Parameters from Nanodevice Development Research Papers

Contact Info

Product

Resources

About