Searching for Named Entities

Named-entity recognition (NER) is a subtask of information extraction that seeks to locate and classify named entities mentioned in unstructured text into pre-defined categories such as person names, organizations, locations, time expressions, quantities, monetary values, etc.

MiaRec voice analytics automatically extract the following names entity classes from a transcript:

Table 1. Supported named entity classes

Named entity class	Description
#CARDINAL	Numerals that do not fall under another type
#DATE	Absolute or relative dates or periods
#EVENT	Named hurricanes, battles, wars, sports events, etc.
#FAC	Buildings, airports, highways, bridges, etc.
#GPE	Countries, cities, states
#LANGUAGE	Any named language
#LAW	Named documents made into laws.
#LOC	Non-GPE locations, mountain ranges, bodies of water
#MONEY	Monetary values, including unit
#NORP	Nationalities or religious or political groups
#ORDINAL	"first", "second", etc.
#ORG	Companies, agencies, institutions, etc.
#PERCENT	Percentage, including "%"
#PERSON	People, including fictional
#PRODUCT	Objects, vehicles, foods, etc. (not services)
#QUANTITY	Measurements, as of weight or distance
#TIME	Times smaller than a day
#WORK_OF_ART	Titles of books, songs, etc.

Using NER classes in MQL expressions

Named entity classes can be included in MQL expression.

For example, the class #PERSON can be used in data redaction expression to automatically remove person names from audio recordings and transcript.

Another sample expression

R"[0-9]+" NOTIN #MONEY

In the above example, we are searching for digits 0 to 9 (using the Regex pattern [0-9]+), but not if they are found inside a text labeled with MONEY class.