L’usage des chatbots fut d’abord en partie expérimental car il présentait un certain risque pour les marques en fonction des dérapages sémantiques possibles et des manipulations ou détournements également envisageables de la part des internautes. Les progrès dans le domaine ont cependant été rapides et les chatbots s’imposent désormais dans certains contextes comme un nouveau canal de support ou contact client garantissant disponibilité et gains de productivité.
Closed domain chatbots focus on a specific knowledge domain, and these bots may fail to answer questions in other knowledge domains. For example, a restaurant booking conversational bot will be able to take your reservation, but may not respond to a question about the price of an air ticket. A user could hypothetically attempt to take the conversation elsewhere, however, closed domain chatbots are not required, nor often programmed to handle such cases.
For as long as I can remember, email has been a fundamentally important channel for a large majority of businesses. The ability to market products directly through a channel that scales up to an incredibly high ceiling is very attractive. The only problem is that it's costing more and more money to acquire email addresses from potential customers, and the engagement from email is getting worse and worse.
“HubSpot's GrowthBot is an all-in-one chatbot which helps marketers and sales people be more productive by providing access to relevant data and services using a conversational interface. With GrowthBot, marketers can get help creating content, researching competitors, and monitoring their analytics. Through Amazon Lex, we're adding sophisticated natural language processing capabilities that helps GrowthBot provide a more intuitive UI for our users. Amazon Lex lets us take advantage of advanced AI and machine learning without having to code the algorithms ourselves.”
The classification score produced identifies the class with the highest term matches (accounting for commonality of words) but this has limitations. A score is not the same as a probability, a score tells us which intent is most like the sentence but not the likelihood of it being a match. Thus it is difficult to apply a threshold for which classification scores to accept or not. Having the highest score from this type of algorithm only provides a relative basis, it may still be an inherently weak classification. Also the algorithm doesn’t account for what a sentence is not, it only counts what it is like. You might say this approach doesn’t consider what makes a sentence not a given class.
Once the chatbot is ready and is live interacting with customers, smart feedback loops can be implemented. During the conversation when customers ask a question, chatbot smartly give them a couple of answers by providing different options like “Did you mean a,b or c”. That way customers themselves matches the questions with actual possible intents and that information can be used to retrain the machine learning model, hence improving the chatbot’s accuracy.
“We believe that you don’t need to know how to program to build a bot, that’s what inspired us at Chatfuel a year ago when we started bot builder. We noticed bots becoming hyper-local, i.e. a bot for a soccer team to keep in touch with fans or a small art community bot. Bots are efficient and when you let anyone create them easily magic happens.” — Dmitrii Dumik, Founder of Chatfuel
ELIZA's key method of operation (copied by chatbot designers ever since) involves the recognition of clue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses that can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY'). Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent".