Humanist Discussion Group

Humanist Archives: March 27, 2023, 7:53 a.m. Humanist 36.484 - numbers for words: advantages?

              Humanist Discussion Group, Vol. 36, No. 484.
        Department of Digital Humanities, University of Cologne
                      Hosted by DH-Cologne
                Submit to:

        Date: 2023-03-26 14:25:06+00:00
        From: Henry Schaffer <>
        Subject: Using numbers for words?

I was at a workshop about large scale computer processing with neural
networks/AI and Natural Language Processing (NLP) came up briefly. The
presenter mentioned that typically numbers were substituted for words - but
didn't discuss why. She referred us to as a method, and there's
some more explanation at

I can see an advantage in storage and processing speed when dealing with a
word represented as perhaps 2 bytes rather than using perhaps 10-20+ bytes
per word, but I don't see any additional advantage. Do you?

Representing a word as a vector allows more information to be kept (as in
word2vec) and so that could give other advantages.

Can anyone add more explanation/reasons?


Unsubscribe at:
List posts to:
List info and archives at at:
Listmember interface at:
Subscribe at: