LFS AI - Best Practices For Building Response Library
Important Considerations
Consider a phrase for each question, then create a simple question for that keyword or phrase.
Add relevant related/similar questions. Refer Add Alternative Question.
Do not use answers such as yes and no.
Use distinct words to differentiate questions
LFS AI performs best when each question addresses a different need. The use of the same word set between questions reduces the likelihood that the right answer is chosen for a question asked.
How about getting into technicals about LFS AI?
When a user performs a search in LFS, LFS AI preprocesses the search text/question with language detection, spellers, and word breakers.
The above alterations are taken into consideration for the best search results.
LFS uses syntactic and semantic based featurization to determine the similarity between the questions and the retrieved search results.
It determines the new ranking order based on the above AI techniques and features.
Features used include, but are not limited to, word-level semantics, term-level importance in a corpus, and deep learned semantic models to determine similarity and relevance between two text strings.