Distributional hypothesis: Difference between revisions
Jump to navigation
Jump to search
mNo edit summary |
mNo edit summary |
||
| Line 1: | Line 1: | ||
{{name|The distributional hypothesis}} | {{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". | 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, | 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 | |||
For example, | |||
[https://en.wikipedia.org/wiki/Distributional_semantics distributional semantics] still says little more than "we look at distributions". | |||
<!-- | |||
'''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. | |||
--> | --> | ||
Revision as of 01:12, 23 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 still says little more than "we look at distributions".