As companies consider adding voicebots to their customer service, they are experiencing the same "Achilles’ heel" with NLU voicebots as they do with chatbots.These issues are the following (the fourth one only applies to voicebots):
One of the flaws of usual training data generation is that, when you ask somebody to manually create training data for you, they will make an effort to write these sentences correctly, following the spelling and punctuation norms of your language. Even if some errors appear, they will be minimal, because they are trying to do things right —this is, to provide “orthographically right” sentences.
All Machine Learning (ML) engines that work with text can benefit from a solid linguistic background. If they are working in a multilingual environment, the need of a good lexicon (with forms, lemmas and attributes) is overwhelming. Even so, basic features such as Word Embeddings hugely improve when enriched with linguistic knowledge, and if this is not usually applied, is because of a lack of linguists working for ML companies.
A chatbot offers significant advantages: it allows your customer support to be omnichannel —i.e. customers will be able to approach you via written chat, voice chat, email, phone, etc.—; it will save you the costs of hiring many additional employees, while sparing you the need of training agents every time your product changes; your customers’ satisfaction will increase; finally, you will get more and more sales (because well-taken-care-of visitors tend to become loyal and regular customers).