-4

I am new LUIS AI.
I would like to train luis for my bot users who wants to buy books online. It is possible to enter I want XYZ, where XYZ is a book or I want ABC, where ABC is an author. They can write find, find out, search, searching, looking, would like to see, would like to find or anything they want to write.

My requirement is to begin with an excel-sheet with utterances and entities and when I upload it, click on train, the application should be trained enough to handle all such user input, at least 90%.

The problem here is how should I write utterances to handle huge probability of user input. I have already approx 65 utterances which includes relevant and diverse utterance but still it is not getting trained to handle all user input.

Please suggest me how to proceed with the utterances to meet this requirement.

Konrad Siamro
  • 213
  • 6
  • 18
user3313361
  • 13
  • 2

1 Answers1

0

Scientist often take 30 minutes of conversation or 200 utterances as a good enough sample to conduct research [1] That is an order of magnitude estimate that is good to know and compare ourselves to.

Now, to get the most variability of incoming utterances, one must find a good origin of similar requests. For my case, sites like yahoo answers is great for finding the usual structure of requests on the topic I work into. I would suggest you to find a place where people query with a similar objective: Google adwords helper is a general but solid start.

[1] http://www.scielo.br/scielo.php?pid=S1516-18462015000401143&script=sci_arttext&tlng=en

Ricardo Alanís
  • 16
  • 1
  • Thanks buddy. I find it a **good approach** to go.Next, I seek you suggestion that what if i do find anne, find betty, find chris,......till find zeniffer. Notice here that I used only find keyword and used names a-z. This is actually helping when i train my luis and ask, say _can you find harry?_ or _it will be great if you find Aesop_ This all are actually working. So my question is **Is this a good approach? Will this create a problem in longer run?** Although i did not see any example over internet using my way. Please suggest – user3313361 Apr 14 '17 at 04:42
  • Sorry about the delay. But certainly: Luis trains over structure and starts guessing a words role after a couple of similar tagged utterances are given it. – Ricardo Alanís Jun 27 '17 at 18:41