Distributional hypothesis: Difference between revisions

From Helpful
Jump to navigation Jump to search
mNo edit summary
 
(4 intermediate revisions by the same user not shown)
Line 1: Line 1:
The distributional hypothesis is the idea that  
'''{{name|The distributional hypothesis}}''' is the idea that words that are used and occur in the same contexts tend to convey similar meanings - "a word is characterized by the company it keeps".
words that are used and occur in the same contexts tend to convey similar meanings - "a word is characterized by the company it keeps".
 
This seems e.g. supported by the way language learners pick up the likely meaning of new words.




This idea is known under a few names,  
This idea is known under a few names,  
but note that few of them really describe a technique,
but note that few of them really describe a very specific or technique or further assumptions they make.
or even the specific assumptions they make.


<!--


Distributional Similarity
For example,
[https://en.wikipedia.org/wiki/Distributional_semantics distributional semantics] says "we do that by looking at distributions", but actually little more than that.


Distributional semantics
<!--
https://en.wikipedia.org/wiki/Distributional_semantics
'''Distributional similarity''' can refer to analysis to bring those out, often for the goal of figuring the relevant semantics,
and that sometimes describes automated techniques that are actually a little more more curated 'just a lot of text at it'.


'''Distributional similarity''' can refer to analysis to bring those out, often for the goal of figuring the relevant semantics.
Say, you could look at noun-verb combinations
and maybe say something about the similarity of nouns based on what verbs they often appear with.
-->


 
Z S Harris (1954) "{{search|Harris 1954  "Distributional Structure"|Distributional Structure}}"
for example on noun-verb combinations, this can be referred to as .
This also means being able to, in that example, being able to e.g. predict noun similarity based on their likeliness of combination with the same verbs.
 
-->

Latest revision as of 13:41, 28 March 2024

The distributional hypothesis is the idea that words that are used and occur in the same contexts tend to convey similar meanings - "a word is characterized by the company it keeps".

This seems e.g. supported by the way language learners pick up the likely meaning of new words.


This idea is known under a few names, but note that few of them really describe a very specific or technique or further assumptions they make.


For example, distributional semantics says "we do that by looking at distributions", but actually little more than that.


Z S Harris (1954) "Distributional Structure"