Claims:WE CLAIM:
1. A method for identifying one or more Places of Interest (PoI) (107) in a natural language input (101), the method comprising:
retrieving, by a natural language processing system (103), a word embedding representation (211) for each word of one or more words in the natural language input (101) from a knowledge repository (105) associated with the natural language processing system (103);
tagging, by the natural language processing system (103), each word with a corresponding Part-of-Speech (POS) (213);
generating, by the natural language processing system (103), a dependency label (215) for each word based on a dependency parser tree for the natural language input (101);
assigning, by the natural language processing system (103), a PoI tag (216) for each word based on the word embedding representation (211), the POS (213), and the dependency label (215) corresponding to each word; and
identifying, by the natural language processing system (103), the one or more PoI (107) in the natural language input (101) based on the PoI tag (216) of each word.

2. The method as claimed in claim 1, wherein the word embedding representation (211) provides semantic and syntactic significance of each word, with respect to context of each word in the natural language input (101).

3. The method as claimed in claim 1, wherein the dependency parser tree is generated based on dependencies among each word in the natural language input (101).

4. The method as claimed in claim 1, wherein the dependency label (215) indicates relative significance of each word in the natural language input (101).

5. The method as claimed in claim 1, wherein assigning the PoI tag (216) for each word is performed using an artificial neural network classifier.

6. The method as claimed in claim 5 comprises training the artificial neural network classifier by performing steps of:
collecting natural language input (101) samples from one or more data sources;
associating each word in the natural language input (101) samples with corresponding PoI tag (216); and
providing the PoI tag (216), associated with each word, to the neural network classifier for training the neural network classifier.

7. The method as claimed in claim 1, wherein the PoI tag (216) is one of a Begin PoI tag, an Inside PoI tag, and a non-PoI tag.

8. A natural language processing system (103) for identifying one or more Places of Interest (PoI) (107) in a natural language input (101), the natural language processing system (103) comprises:
a processor (203); and
a memory (205), communicatively coupled to the processor (203), wherein the memory (205) stores processor-executable instructions, which on execution, cause the processor (203) to:
retrieve a word embedding representation (211) for each word of one or more words in the natural language input (101) from a knowledge repository (105) associated with the natural language processing system (103);
tag each word with a corresponding Part-of-Speech (POS) (213);
generate a dependency label (215) for each word based on a dependency parser tree for the natural language input (101);
assign a PoI tag (216) for each word based on the word embedding representation (211), the POS (213) , and the dependency label (215) corresponding to each word; and
identify the one or more PoI (107) in the natural language input (101) based on the PoI tag (216) of each word.

9. The natural language processing system (103) as claimed in claim 8, wherein the word embedding representation (211) provides semantic and syntactic significance of each word, with respect to context of each word in the natural language input (101).

10. The natural language processing system (103) as claimed in claim 8, wherein the processor (203) generates the dependency parser tree based on dependencies among each word in the natural language input (101).

11. The natural language processing system (103) as claimed in claim 8, wherein the dependency label (215) indicates relative significance of each word in the natural language input (101).

12. The natural language processing system (103) as claimed in claim 8, wherein the processor (203) assigns the PoI tag (216) for each word using an artificial neural network classifier.

13. The natural language processing system (103) as claimed in claim 12, wherein to train the artificial neural network classifier, the processor (203) is configured to:
collect natural language input (101) samples from one or more data sources;
associate each word in the natural language input (101) samples with corresponding PoI tag (216); and
provide the PoI tag (216), associated with each word, to the neural network classifier to train the neural network classifier.

14. The natural language processing system (103) as claimed in claim 8, wherein the PoI tag (216) is one of a Begin PoI tag, an Inside PoI tag, and a non-PoI tag.

Dated this 23rd day of January 2018

SWETHA S. N
OF K&S PARTNERS
ATTORNEY FOR THE APPLICANT , Description:TECHNICAL FIELD
The present subject matter is generally related to artificial intelligence and more particularly, but not exclusively, to a method and system for identifying one or more Places of Interest (PoI) in a natural language input.