Automatically Extract Entities Into Actionable Objects
Included standard with DataWalk is an entity extraction facility with over 60 languages supported. This facility automatically parses text documents to identify text content that represents things like names of people, locations, dates, and various other types of objects. These entities can then be linked to existing data already in DataWalk using various techniques. DataWalk has also integrated with third party entity resolution products such as Rosoka and Rosette.
Effectively Process Data In Foreign Languages
DataWalk includes a very effective translation capability for over 1000 language pairs. You can import documents in languages including French, Spanish, Chinese, Russian and many others, and then do entity extraction of the translated documents.
Automatically Identify Text Patterns
DataWalk enables you to configure a dictionary of terms and phrases of any kind that are of interest to you, such that text which references these terms can be automatically identified. For example, you may be interested in identifying if phrases associated with a particular person, company, weapon, or anything else are present in text content. In such cases you can create a dictionary of these terms or patterns of interest, and DataWalk can automatically identify where these terms exist in your text content.