Humanist Discussion Group, Vol. 36, No. 496.
Department of Digital Humanities, University of Cologne
Hosted by DH-Cologne
www.dhhumanist.org
Submit to: humanist@dhhumanist.org
Date: 2023-03-29 14:28:14+00:00
From: James Rovira <jamesrovira@gmail.com>
Subject: Re: [Humanist] 36.489: numbers for words
These posts have been interesting and informative to me, and I'm grateful
for them.
Michael --
Are there any models that take into account polysemy in your example no. 2
below? Not just that a word has multiple meanings, but that a single text
can exploit multiple meanings of the same word even within the same
sentence? The word "father" can be a noun or a verb, for example, and has
seven definitions as a noun and three as a verb just in Miriam Webster.
Jim R
On Wed, Mar 29, 2023 at 1:36 AM Humanist <humanist@dhhumanist.org> wrote:
>
> 2. As a word => one number per word
>
> In most NLP applications, it makes more sense to train the model on the
> words in
> the data rather than the letters. The biggest reason for this is that the
> words
> are the main unit of meaning, and the sequence of data the computer has to
> analyse is shorter. So, for example, ‘the cat sat on the mat’ contains 6
> words,
> but 23 characters (including spaces). The computer has to perform fewer
> calculations if it is examining only 6 words rather than 23 characters. In
> addition, in a word-encoding scheme, ‘cat’ and ‘sat’ are simply two
> different
> words. If you let the computer see ‘c-a-t’ and ‘s-a-t’, it has a harder
> learning
> task, because it won’t know in advance that ‘cat’ and ‘sat’ are totally
> different: 2/3 of the letters are the same!
>
>
_______________________________________________
Unsubscribe at: http://dhhumanist.org/Restricted
List posts to: humanist@dhhumanist.org
List info and archives at at: http://dhhumanist.org
Listmember interface at: http://dhhumanist.org/Restricted/
Subscribe at: http://dhhumanist.org/membership_form.php
