Handling Edge Cases

Misspellings

Spelling errors can affect both entity extraction and intent classification. Coming across misspellings is inevitable, so your bot needs an effective way to handle this. Keep in mind that the goal is not to correct misspellings, but to correctly identify intents and entities. For this reason, while a spellchecker may seem like an obvious solution, adjusting your training data is often sufficient to account for misspellings.

we should have add some misspelled words, it will work well with only a few examples.

Your data must reflect how users talk to your bot.

If your users do spelling mistakes, then your training data should have some too.