Semantic Analysis of Words and Sentences in Natural Language Processing

Coming up with a numerical representation of the semantics (meaning) of words and sentences can be tricky. This is especially true for “fuzzy” languages like English, which has multiple dialects and many different interpretations of the same words.

Even formal English text written by an English professor can’t avoid the fact that most English words have multiple meanings, a challenge for any new learner, including
machine learners. 

Polysemy
This concept of words with multiple meanings is called polysemy:

The existence of words and phrases with more than one meaning Here are some ways in which polysemy can affect the semantics of a word or statement. We list them here for you to appreciate the power of LSA. You don’t have to worry about these challenges. LSA takes care of all this for us:

# Homonyms

Words with the same spelling and pronunciation, but different meanings

# Zeugma

Use of two meanings of a word simultaneously in the same sentence
And LSA also deals with some of the challenges of polysemy in a voice interface - a chatbot that you can talk to, like Alexa or Siri.

# Homographs

Words spelled the same, but with different pronunciations and meanings

# Homophones

Words with the same pronunciation, but different spellings and meanings (an NLP challenge with voice interfaces).

Imagine if you had to deal with a statement like the following, if you didn’t have tools like LSA to deal with it:

She felt ... less. She felt tamped down. Dim. More faint. Feint. Feigned. Fain.
--Patrick Rothfuss 

Tags: Natural Language Processing,