0

There are already spell checking models available which help us to find the suggested correct spellings based on a corpus of trained correct spellings. Can the granularity be increased to "word" from alphabet so that we can have even phrase suggestions , such that if an incorrect phrase is entered then it should suggest the nearest correct phrase, of course it is trained from a list of valid phrases.

Are there any existing tools and approaches which achieve this functionality or how to proceed for this for an existing large gold standard phrase corpus, say the manchester academic phrasebank ?

Improve this question
4
  • See stackoverflow.com/questions/2901831/algorithm-for-autocomplete or stackoverflow.com/questions/1783652/… – prash♦ Aug 5 '15 at 12:49
  • @prash its not autocomplete but suggesting phrases using statistical learning of a preset corpus – lingo101 Aug 5 '15 at 13:01
  • Well... you did ask for word-level granularity. In any case, word autocompletion can be made to handle phrases too. And you can change the training models for any of them, just as you would with spelling correction algos. – prash♦ Aug 5 '15 at 13:46
  • @prash yes , it would be nice to know what options are availiable for a limited phrasebank, the words being limited in a phrasebank like how alphabet are finite in a string – lingo101 Aug 5 '15 at 13:59

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.