Difference between revisions of "Ideas for Google Summer of Code/Corpus-based lexicalised feature transfer"

From Apertium
Jump to navigation Jump to search
 
(2 intermediate revisions by one other user not shown)
Line 19: Line 19:
   
 
==Frequently asked questions==
 
==Frequently asked questions==
  +
* none yet, ''[[contact|ask us]] something!'' :)
   
 
==See also==
 
==See also==
Line 25: Line 26:
 
* [[Pronoun verb combinations in Romance languages]]
 
* [[Pronoun verb combinations in Romance languages]]
 
* [[Choosing genitive structure in English]]
 
* [[Choosing genitive structure in English]]
  +
* [[User:Fpetkovski/GSOC 2012 Report]]
  +
* [http://www.mt-archive.info/10/AMTA-2014-Weller.pdf Using Noun Class Information to Model Selectional Preferences for Translating Prepositions in SMT]
   
 
[[Category:Ideas for Google Summer of Code|Closer integration with HFST]]
 
[[Category:Ideas for Google Summer of Code|Closer integration with HFST]]

Latest revision as of 11:19, 9 February 2015

Make a module that sits somewhere in the Apertium pipeline (somewhere after the lexical selection and before morphological generation) that sets features (e.g. tags) based on a model generated from a corpus. Sometimes we get really inadequate translations even though you'd never hear stuff like that.

One of those things is when we output something as definite when it is never used as definite. One way of dealing with this is a lot of rules and lists in transfer, but those are hard to do. So, how about looking at a corpus for information about some features like definiteness, aspect, evidentiality, impersonal/reflexive pronoun use in Romance languages etc.

Tasks[edit]

  • Make a corpus study of one possible feature, the treatment of which could be improved with target-language information.
  • Experiment with including a statistical model based on this feature in the Apertium pipeline
  • Make a prototype implementation (possibly in python)
  • Generalise the prototype to deal with other features
  • Come up with an efficient format for storing the model.
  • Implement the final program efficiently in C++.

Coding challenge[edit]

  • Make a stream processor (see Apertium stream format) for the output of apertium-transfer (both default/chunk possibilities) that parses character by character.

Frequently asked questions[edit]

  • none yet, ask us something! :)

See also[edit]