"Modern conversational agents (chatbots) tend to be highly specialized — they perform well as long as users don’t stray too far from their expected usage.This is the 'Chinese Room' approach to social agency, consciousness not required.
To better handle a wide variety of conversational topics, open-domain dialog research explores a complementary approach attempting to develop a chatbot that is not specialized but can still chat about virtually anything a user wants.
Besides being a fascinating research problem, such a conversational agent could lead to many interesting applications, such as further humanizing computer interactions, improving foreign language practice, and making relatable interactive movie and videogame characters.
However, current open-domain chatbots have a critical flaw — they often don’t make sense. They sometimes say things that are inconsistent with what has been said so far, or lack common sense and basic knowledge about the world. Moreover, chatbots often give responses that are not specific to the current context.
For example, “I don’t know,” is a sensible response to any question, but it’s not specific. Current chatbots do this much more often than people because it covers many possible user inputs.
In “Towards a Human-like Open-Domain Chatbot”, we present Meena, a 2.6 billion parameter end-to-end trained neural conversational model. We show that Meena can conduct conversations that are more sensible and specific than existing state-of-the-art chatbots. Such improvements are reflected through a new human evaluation metric that we propose for open-domain chatbots, called Sensibleness and Specificity Average (SSA), which captures basic, but important attributes for human conversation.
Remarkably, we demonstrate that perplexity, an automatic metric that is readily available to any neural conversational models, highly correlates with SSA..."
Read more...
I think the approach is architecturally self-limiting: the limit-point being suave, fluid, empty-headed gossip-grooming.
It will make Google a fortune.
Are Eliza - style (in behaviour if not construction) Chatbots really going to make Google a lot of money? I can see a possible use for them in Retirement Homes, but otherwise they need to be part of a(n Android) - a wider system with goals.
ReplyDeleteA problem solving Chatbot would be more useful (Alexa Plus Plus?): e.g. "what do I need to do to fix a broken radiator?"
Yes, we've had this (social-agency) discussion before. Yet really good mimicry has a quality all of its own. An automated system which can reflect back to you something basically-appropriate over quite a few conversational turns would have many applications. Link it to some personalised, crystallized knowledge about you and working memory and you have a viable robot companion ...
Delete