“For these algorithms to work, we need to select some features from text. Some of the commonly used features for NER are unigram, left and right bigrams and trigrams, part of speech tags, whether the word is capitalized or not, is the first character capitalized or not, whether the word is surrounded by quotes or not, is there a hyphen in the word, is the word present in our gazetteer list (it's a list which would contain names of people, organizations, locations, etc. mined from various sources like Wikipedia and Freebase), word suffixes and prefixes, .”
Tagged: NER, NLP

Explore more quotes:


About the author

This page was created by our editorial team. Each page is manually curated, researched, collected, and issued by our staff writers. Quotes contained on this page have been double checked for their citations, their accuracy and the impact it will have on our readers.

Kelly Peacock is an accomplished poet and social media expert based in Brooklyn, New York. Kelly has a Bachelor's degree in creative writing from Farieligh Dickinson University and has contributed to many literary and cultural publications. Kelly assists on a wide variety of quote inputting and social media functions for Quote Catalog. Visit her personal website here.

Kendra Syrdal is a writer, editor, partner, and senior publisher for The Thought & Expression Company. Over the last few years she has been personally responsible for writing, editing, and producing over 30+ million pageviews on Thought Catalog.