What are NER Concepts?
Understanding how NER concepts facilitate your analyses.
NER, or Named Entity Recognition, is a deep learning text analytics subdomain where terms and phrases are identified within unstructured text and classified into categorical (aka entity) types (e.g. proteins, cell line, disease, companies, etc.). We use NER tagging to create NER Concepts, which appear in several areas of Layar. Some examples of how we leverage NER Concepts include Filters By Concept Type (Axon Specific), the Document View, and the NER Concept Graph.
We automatically apply NER tagging to all of the text that is given to Layar. This means you’ll find NER tagging in articles, PDFs, spreadsheets, RSS feeds, and any other data you have added that has text available. You can see these tags by clicking on the single document or piece of data and viewing it in the Document View.
This is an example of NER tagging in a snippet of text for a PDF:
This is an example of NER tagging in a spreadsheet with text:
Here are some example NER tags that we use to annotate text:
Life Science NER Tags
We have built out over twenty different NER concept types for the life science domain, ranging from diseases to proteins to simple chemicals. This list continues to grow every day – but here is an example of some of the NER concepts we can pick up:
Chemical of Biological Interest
Gene or Gene Product
Immaterial Anatomical Entity
Multi Tissue Structure
Business Development NER Tags
Organization - a company, non-profit, or institution.
Person - an author, board member, etc.
Location - a country, city, region, etc.
Custom NER Tags
We can also provide custom NER tagging models for your team. Please contact us for more details.