Difference between revisions of "Word-sense disambiguation"

From Apertium
Jump to navigation Jump to search
(Category:Documentation in English)
 
(One intermediate revision by the same user not shown)
Line 1: Line 1:
'''Word sense disambiguation''' is important in machine translation between less-closely related languages. The problem was elucidated most famously by Yehoshua Bar-Hillel, who asks us to consider the following sentence:
+
'''Word sense disambiguation''' means choosing between two ''meanings'' of the same word (we assume we already know the part of speech). This can be important in machine translation between less-closely related languages. The problem was elucidated most famously by Yehoshua Bar-Hillel, who asks us to consider the following sentence:
   
 
:Little John was looking for his toy box. Finally he found it. The box was in the pen.
 
:Little John was looking for his toy box. Finally he found it. The box was in the pen.
Line 10: Line 10:
 
To a human, the meaning is obvious, but Bar-Hillel claimed that without a "universal encyclopaedia" a machine would never be able to deal with this problem. Figuring out which sense to use when a word is ambiguous is called ''word sense disambiguation'', and is a big research area.
 
To a human, the meaning is obvious, but Bar-Hillel claimed that without a "universal encyclopaedia" a machine would never be able to deal with this problem. Figuring out which sense to use when a word is ambiguous is called ''word sense disambiguation'', and is a big research area.
   
  +
However, importantly, many of the possible meanings and nuances identified by lexicographers ''do not affect machine translation''. E.g. the English term ''hospital'' can refer to both an organisation and a concrete building, but regardless of which meaning is used in a sentence, in Norwegian it still becomes ''sjukehus''. Thus we use the term '''lexical selection''' when we speak of those word senses that matter to MT. More on this in the article [[Lexical selection]].
==Lextor==
 
{{main|Lextor}}
 
   
Lextor is the current word sense disambiguation module for Apertium, it works using statistics and requires 1) slightly pre-processed dictionaries and 2) corpora to train the module. '''The module is turned off in most cases as it does not provide an improvement over the baseline.'''
 
 
==See also==
 
 
* [[Lexical selection in target language]]
 
* [[Limited rule-based lexical selection]]
 
   
 
==Further reading==
 
==Further reading==

Latest revision as of 10:38, 7 September 2012

Word sense disambiguation means choosing between two meanings of the same word (we assume we already know the part of speech). This can be important in machine translation between less-closely related languages. The problem was elucidated most famously by Yehoshua Bar-Hillel, who asks us to consider the following sentence:

Little John was looking for his toy box. Finally he found it. The box was in the pen.

The word pen may have two meanings:

  1. Something you use to write with
  2. A container of some kind

To a human, the meaning is obvious, but Bar-Hillel claimed that without a "universal encyclopaedia" a machine would never be able to deal with this problem. Figuring out which sense to use when a word is ambiguous is called word sense disambiguation, and is a big research area.

However, importantly, many of the possible meanings and nuances identified by lexicographers do not affect machine translation. E.g. the English term hospital can refer to both an organisation and a concrete building, but regardless of which meaning is used in a sentence, in Norwegian it still becomes sjukehus. Thus we use the term lexical selection when we speak of those word senses that matter to MT. More on this in the article Lexical selection.


Further reading[edit]