Artificial Intelligence is currently being deployed in customer service to both augment and replace human agents - with the primary goals of improving the customer experience and reducing human customer service costs. While the technology is not yet able to perform all the tasks a human customer service representative could, many consumer requests are very simple ask that sometimes be handled by current AI technologies without human input.
Next, identify the data sources that will enable the bot to interact intelligently with users. As mentioned earlier, these data sources could contain structured, semi-structured, or unstructured data sets. When you're getting started, a good approach is to make a one-off copy of the data to a central store, such as Cosmos DB or Azure Storage. As you progress, you should create an automated data ingestion pipeline to keep this data current. Options for an automated ingestion pipeline include Data Factory, Functions, and Logic Apps. Depending on the data stores and the schemas, you might use a combination of these approaches.
I will not go into the details of extracting each feature value here. It can be referred from the documentation of rasa-core link that I provided above. So, assuming we extracted all the required feature values from the sample conversations in the required format, we can then train an AI model like LSTM followed by softmax to predict the next_action. Referring to the above figure, this is what the ‘dialogue management’ component does. Why LSTM is more appropriate? — As mentioned above, we want our model to be context aware and look back into the conversational history to predict the next_action. This is akin to a time-series model (pls see my other LSTM-Time series article) and hence can be best captured in the memory state of the LSTM model. The amount of conversational history we want to look back can be a configurable hyper-parameter to the model.
As retrieved from Forbes, Salesforce’s chief scientist, Richard Socher talked in a conference about his revelations of NLP and machine translation: “I can’t speak for all chatbot deployments in the world – there are some that aren’t done very well…but in our case we’ve heard very positive feedback because when a bot correctly answers questions or fills your requirements it does it very, very fast.
The classic historic early chatbots are ELIZA (1966) and PARRY (1972). More recent notable programs include A.L.I.C.E., Jabberwacky and D.U.D.E (Agence Nationale de la Recherche and CNRS 2006). While ELIZA and PARRY were used exclusively to simulate typed conversation, many chatbots now include functional features such as games and web searching abilities. In 1984, a book called The Policeman's Beard is Half Constructed was published, allegedly written by the chatbot Racter (though the program as released would not have been capable of doing so).
When we open our news feed and find out about yet another AI breakthrough—IBM Watson, driverless cars, AlphaGo — the notion of TODA may feel decidedly anti-climatic. The reality is that the current AI is not quite 100% turnkey-ready for TODA. This will soon change due to two key factors: 1) businesses want it, and 2) businesses have abundant data, the fuel that the current state-of-the-art machine learning techniques need to make AI work.
The process of building a chatbot can be divided into two main tasks: understanding the user's intent and producing the correct answer. The first task involves understanding the user input. In order to properly understand a user input in a free text form, a Natural Language Processing Engine can be used. The second task may involve different approaches depending on the type of the response that the chatbot will generate.
ALICE – which stands for Artificial Linguistic Internet Computer Entity, an acronym that could have been lifted straight out of an episode of The X-Files – was developed and launched by creator Dr. Richard Wallace way back in the dark days of the early Internet in 1995. (As you can see in the image above, the website’s aesthetic remains virtually unchanged since that time, a powerful reminder of how far web design has come.)
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".