Recent
Blogs.
We write regularly about different terminology and jargon you’ll hear in the text analytics industry. Join us in our blog to make the complex, simple.
Content
Content is a term used to refer to the text that is being analyzed. This can include things like social media posts,…
Correlation
Correlation is used to refer to the relationship between two or more variables. This relationship can be positive, negative, or none at…
Technology-Assisted Review
Technology-Assisted Review (TAR) is defined as a process of using technology to identify, prioritize and categorize documents for review. This process is…
Surface Form
Surface form is defined as the literal meaning of a word or phrase, without taking into account any context clues that could…
Opaque Term
When a term is difficult to parse, it is said to be opaque. An opaque term can be either a single word…
Index Cache
Index cache is a type of software that helps with the retrieval of information from a text corpus. It stores frequently accessed…
Fielded Search
Fielded search is the practice of searching for specific information in a given field or set of fields. For example, a user…
Data Source Type
Data source type is used to describe the origin of the text data being analyzed. This is important because the way the…
Boost Word
Boost word is typically associated with query processing. Query processing is the process of transforming a user’s query into a form that…
Bi Variate
Bi Variate is used to refer to the simultaneous analysis of two variables. For example, sentiment analysis could be conducted on a…
AI Developer Toolkits
AI Developer Toolkits is a term used to describe software development kits that enable the construction of applications that utilize artificial intelligence…
Advanced Anomaly Detection
Advanced Anomaly Detection is a method used to automatically detect outliers in data. This is done by training a model on a…