The Kore.ai NL engine makes the process of building accurate NL-enabled chatbots scalable. It recognizes simple yet critical nuances to a human’s natural language to mitigate potential misinterpretation and prevent developers from designing for every idiomatic variation. It also includes features that let developers easily customize, extend, and reuse vocabulary.
Below are some of the ways our NLP engine intelligently processes the language you use to speak to a bot.
- Multi-sentence messages – Our NLP engine processes every sentence in a message – even if each has a unique intent – which reduces the number of interactions with the user.
- Patterns and idiomatic sentences – Bots already know “what’s it like outside?” means “get current conditions” because Kore.ai’s NLP discards unnecessary words, uses wildcard logic to process intent, remembers user input and understands common phrases.
- Pre-programed synonyms – Includes pre-programmed synonyms and bot responses
- Singular v. plural nouns – Bots process either noun the same way (i.e. sales lead, sales leads) which mitigates potential confusion and prevents developers from creating extra synonyms.
- Capitalization – Bots recognize proper nouns and remove capitalization from common nouns.
- Tensed verbs – Understands a single verb communicated in different tenses as synonymous.
- Contractions – Expands contractions and removes apostrophes to simplify task processing.
- Numeric words vs. digits – Recognizes the communication of numeric values as words or digits
- Vocabulary expansion – Enables addition of synonyms and uses ML to continuously expand chatbot vocabulary
- Vocabulary transfer – Allows for transfer of developed vocabulary from one chatbot to the next
- Message personalization – Replaces default, universal responses with unique, configured messages