Variant Identification and Grouping
Variant identification and grouping allow ThingFinder to accurately classify all relevant entities in a document, even one-word entities, and to provide true counts reflecting the number and location of ALL appearances of a given entity. For example, ThingFinder recognizes that the appearance of the word "Smith" in the example below refers to the earlier identified person "Joe Smith."

Normalization
Normalization takes much of the guesswork out of metadata creation, search, data mining and link analysis processes by creating standard formats (e.g., ISO) for certain entity categories such as dates or measurements.

Relevance Ranking
The entities extracted by ThingFinder are given relevance scores reflecting their importance to the document as a whole, making ThingFinder an essential part of any data categorization solution.

Customization
ThingFinder can be easily extended to identify and extract custom entities, such as project names, patent numbers, personal associations, or travel events.

ThingFinder Professional extends the power of customized discovery to unique entity types and concepts, as well as relationships and events (facts), by letting the user define custom extraction patterns. Enriched with deep understanding of natural language, ThingFinder Professional can extract such custom entity and fact types as date/timestamps, chemical compound names or formulae, serial or part numbers. It can also extract custom facts such as merger and acquisition events, company contact information, brand co-occurrence or medication adverse effects, among many other types of facts.

ThingFinder Professional provides a simple and powerful rule writing language to define patterns for discovery and extraction, including regular expression operators, linguistic operators (word stems, part-of-speech tags, phrase and clause boundaries), list matching, input matching filters, case insensitive matching, and much more.