I need your help to set all rules for extracting names/concepts from a phrase.
for example, in the phrase "in toshka, it's always sunny" the name/concept here is toshka, which is a place in Egypt. i found it because it's a Preposition followed by a Noun
What are other rules for finding entities/names?
|
|
|||||||||||
|
closed as not constructive by Carlo_R., Andrew Leach, Mitch, simchona♦ Sep 26 '12 at 15:22
As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or specific expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, see the FAQ for guidance.
|
This sounds like computational linguistics to me, but it isn’t clear which particular NLP task you actually mean here. If you are just looking for nouns, you probably need a part-of-speech tagger. Note that POS taggers that are not integrated into syntactic analysers do not perform at all as well as those that are. And you are going to need some sort of lemmatizer to reduce to citation forms using inflectional morphology. Because you mention entities, it may also be a matter named-entity recognition. But when you say “concept”, I wonder whether you don’t need something more like the Stanford Event Parser. Now you may also have to work with derivational morphology. Any way you slice it, this is much too complex, and complicated, a topic to be succinctly and definitively answered here. You will need to look into the current state-of-the-art research in CL and NLP. |
|||||||
|
