1

In DevPost Watson Developer Challenge for Conversational Applications post, I saw Watson (maybe) able to analyze following phrase "I want to visit Tokyo, Sydney, Manchester, and Reykjavik during a trip that takes 30 days".

Is there a better way to extract those array of locations without having to predefine max no of location variables (i.e. set location1 - 5) and manually specify various grammar items like $ (Locations)={location1} * (Locations)={location2} * (Locations)={location3} * (Locations)={location4} as per Pizza example dialog? I would like to follow up with comment such as "That's a lot" if location > 4, or "Sure" if less.

totoro
  • 195
  • 1
  • 9
  • As far as I know, this is the *recmmended* way, I would love to see a different answer – Dudi Apr 03 '16 at 18:02
  • I was hoping EntityType LOCATION could gives me list of recognized places - much like DATE_TIME_RANGE which could intelligently convert "yesterday" into appropriate date. But there isn't much documentation on such features. Alternatively is to use Watson Relationship Extraction Service to recognize the entities - but performance may suffer, because I need to use various call to get things done. – totoro Apr 04 '16 at 00:02

1 Answers1

0

You could try something like alchemy or relationship extraction to identify all of the languages, and then simply add them to the user profile in Dialog. But today, the best way to do this within a broader conversation will be to do it the same way the pizza sample does as you outlined above.

Mitch
  • 849
  • 4
  • 4