0

I am working on a nlp project where i have to determine word context in a sentence forexample the word crane, for instance, could refer to a machine used to lift heavy objects, a type of bird, or even a movement of someone’s neck.
and i do not know how to proceed. I am using NLTK Python and wordnet. with wordnet i can find out the meaning of word but how to get the appropriate context of word. Like - i saw a crane flying then i want a result like crane with referring to bird with score

user1190312
  • 1
  • 1
  • 4
    The context is usually either a window of *n* word tokens (eg. 5) to the left and right of the target word, or all tokens in the same sentence or paragraph. However, the context won't magically link to one of the WordNet synsets. The task you are trying to solve is called Word Sense Disambiguation (WSD); go search for that. I wouldn't call it a solved problem, but there are established approaches. Most recently, word embeddings have shown good results. – lenz May 03 '17 at 08:36
  • Thanks lenz for providing useful information. – user1190312 May 03 '17 at 09:42
  • similar to https://stackoverflow.com/questions/22118136/nltk-find-contexts-of-size-2k-for-a-word – Tanya Gupta Aug 04 '19 at 16:57

0 Answers0