Facebook wants to make its AI chatbots more human

Just over a year since Facebook first unveiled its chatbots, the social networking giant isn't done making improvements to dialog-driven assistants.

Today, Facebook Artificial Intelligence Research (FAIR) released a new framewrok for developers intended to help fine-tune and improve the conversational abilities of chatbots, of which Facebook Messenger has over 11,000 of and growing.

ParlAI (pronounced like "parley," if you were curious) is an open-source framework of over 20 different Python-based datasets for training and researching dialog models that power the everyday chatbots.

FAIR believes that by supplying a unified platform for researchers and developers, chatbots can use the data gathered by the ParlAI community to make chatting with a bot faster and more human rather than, well, robotic.

One example of how ParlAI could improve chatbots is its potential to improve multitasking. By teaching a dialog model to understand more than one sentence at a time, a chatbot can handle more natural conversation instead of short or stilted single commands.

ParlAI isn't FAIR's first pass at improving artificial intelligence, either. The open-source framework joins the likes of FastText, which helps AIs classify text quickly, and CommAI, a general repository for artificial general intelligence, as other Facebook-backed tools designed to put the social media company on the bleeding edge of AI research.