Document Annotation: The Scribe
The Scribe is a manuscript annotation service that recognizes important terms in a document and embeds semantic links to authoritative resources.
We offer this service to publishers to automatically screen raw manuscripts (in Microsoft Word, OpenOffice or XML format) for adherence to a journal stylesheet, validate correct use of selected terminologies and nomenclatures, verify specific cited resources, summarize those resources in a standardized form to simplify "fact-checking" by editors/peer reviewers, embed persistent links into the manuscript that flow through into the published article and annotates factual errors that require review by editor/peer-reveiwer/author.
The service ensures consistency and completeness of each article and reduces time and effort for peer-reviewers and authors, who need only to check manuscripts for technical soundness. The service uses a simple drag and drop interface. Editors can select/deselect different terminologies, identifier classes and other research artifacts to check and link. The service returns a completely marked-up and annotated version, typically in less than one minute.
Rich Content: The N4L::Guide
Authoritative Microbiology Resources
The NamesforLife Taxonomic Abstracts
Since 2006, our company has provided freely accessible taxonomic abstracts that provide curated, up to date, authoritative nomenclature and taxonomy for all validly published prokaryotes.
In 2014 we launched the StrainFinder service, which resolves strain identifiers to deposits at Biological Resource Centers (BRCs).
This service can be used as a web-based search portal for prokaryotic strains, but it is also integrated with the Scribe to embed persistent links to deposits without linking directly to individual culture collections (whose links are not guaranteed to be permanent).
Custom software based on NamesforLife components
Our company has developed several innovative software components to overcome technical barriers in text mining, information extraction, document classification and annotation.
We have developed powerful grammars that are able to precisely identify complex terms such as chemical entities, scientific names and many classes of unique identifiers.
A KWIC index provides a view the context of any phrase across all documents in a corpus.
Our unique visualization tools can help to quickly locate the diagnostic terms for groups of related documents, which can greatly expedite the patent examination process and assist with IP valuation.
Our classification tools provide novel ways to navigate and bridge various patent classification systems, enabling more precise classification and integration with additional proprietary classifications.
These individual software components have been integrated into a single platform that can support a variety of document analysis needs. Our software may be deployed in a web service container, as a desktop application, or extended/integrated with third party software via our developer API.
Backed by the Fairview Research Alexandria platform (CLAIMS® Global Patent Database), this analysis suite has access to the full text of the worldwide patent literature.
The Semantic Desktop is a document classification application built upon this platform. We demonstrate the ability to reverse-engineer the diagnostic phrases that human indexers use to classify large corpora of technical documents, and to measure both the quality of previously-annotated documents and the cohesion of individual document classifications.