Google is working towards its best digital assistant that is capable of having a conversation based Artificial Intelligence (AI) model known as Meena.
Meena, a neural network that has 2.6 billion parameters, is a multi-turn open-domain chatbot and claimed to be better than any other AI chatbot available in the market.
Conversational AI is a comprehensive term used to natural language models for AI that understand human language, speak and completes tasks given in simple words.
However, talking and carrying a Conversation are both different tasks as AI assistants like Alexa, Siri, Google doesn't really chat — they just complete tasks and answers factual questions.
Holding a human-like conversation is still very much impossible for the smart assistants available today.
To check the skills and capacity of a conversational agent, Google released a system of measurement called Sensibleness and Specificity Average (SSA).
SSA helps to maintain answers in a conversation and makes sure that they are relevant and understandable.
SSA ranks the conversation by evaluating the static performance mixed with genuine interaction — The performance results are based on the percentage of turns counted as relevant or sensible.
SSA tool give a score of 79% to Meena, Pandora Bots AI Agents, Mitsuku got 56%, Microsoft’s Mandarin Chinese Chinese speaking XiaoIce got 31%, while human got 86%.
All the conversations had to last between 14 to 28 turns, and bots that give general answers get the penalty.
AI assistants that are capable of holding human-like conversations might become an essential part of human life, as they could provide moral or emotional support to their owners said by Ashwin Ram, the Alexa prize head and Google Research director.
Besides Google, Microsoft also working on Bot Framework — last year they began showing more multi-turn dialogue for users, and also acquired Semantic Machines in 2018.
Last year, Amazon introduced a feature called "Conversations" that packages voice application suggestions in conversational multi-turn dialogue. It was called “the holy grail of voice science” by the VP of devices David Limp.
Read next: Latest Deepfake Technology Create More Convincing Videos Based on Audio Source Than Ever Before
Meena, a neural network that has 2.6 billion parameters, is a multi-turn open-domain chatbot and claimed to be better than any other AI chatbot available in the market.
Conversational AI is a comprehensive term used to natural language models for AI that understand human language, speak and completes tasks given in simple words.
However, talking and carrying a Conversation are both different tasks as AI assistants like Alexa, Siri, Google doesn't really chat — they just complete tasks and answers factual questions.
Holding a human-like conversation is still very much impossible for the smart assistants available today.
To check the skills and capacity of a conversational agent, Google released a system of measurement called Sensibleness and Specificity Average (SSA).
SSA helps to maintain answers in a conversation and makes sure that they are relevant and understandable.
SSA ranks the conversation by evaluating the static performance mixed with genuine interaction — The performance results are based on the percentage of turns counted as relevant or sensible.
SSA tool give a score of 79% to Meena, Pandora Bots AI Agents, Mitsuku got 56%, Microsoft’s Mandarin Chinese Chinese speaking XiaoIce got 31%, while human got 86%.
All the conversations had to last between 14 to 28 turns, and bots that give general answers get the penalty.
AI assistants that are capable of holding human-like conversations might become an essential part of human life, as they could provide moral or emotional support to their owners said by Ashwin Ram, the Alexa prize head and Google Research director.
Besides Google, Microsoft also working on Bot Framework — last year they began showing more multi-turn dialogue for users, and also acquired Semantic Machines in 2018.
Last year, Amazon introduced a feature called "Conversations" that packages voice application suggestions in conversational multi-turn dialogue. It was called “the holy grail of voice science” by the VP of devices David Limp.
Read next: Latest Deepfake Technology Create More Convincing Videos Based on Audio Source Than Ever Before
