Top
Begin typing your search above and press return to search.
exit_to_app
Outlook for BJP in Kerala
access_time 2021-05-06T11:21:07+05:30
Not Covid deaths, but mass murder
access_time 2021-05-05T10:52:36+05:30
Poll results that carry lessons
access_time 2021-05-04T10:39:06+05:30
DEEP READ
Iran and the revival of JCPOA
access_time 2021-04-23T13:21:09+05:30
A model mosque in Gujarat
access_time 2021-04-12T17:13:34+05:30
Towards a digital emergency?
access_time 2021-02-27T14:50:41+05:30
The slaughter of democracy in Puducherry
access_time 2021-02-24T11:27:21+05:30
Populist Fascism
access_time 2021-01-31T17:19:29+05:30
Media Freedom
access_time 2021-01-31T15:47:07+05:30
exit_to_app
Homechevron_rightTechnologychevron_rightFacebook AI team...

Facebook AI team teaching chatbots how to talk like humans

text_fields
bookmark_border
Facebook AI team teaching chatbots how to talk like humans
cancel

San Francisco: Facebook Artificial Intelligence Researchers (FAIR) have tested a new approach that teaches bots how to chit-chat like humans.

The team used a special 164,000-utterance data set titled "Persona-Chat" to teach its AI to look for patterns.

"Persona-Chat" consists of more than 160,000 lines of dialogue, sourced from workers found on Amazon's "Mechanical Turk" marketplace, The Verge reported on Monday.

Amazon Mechanical Turk (MTurk) is a crowdsourcing Internet marketplace enabling individuals and businesses to coordinate the use of human intelligence to perform tasks that computers are currently unable to do.

In the Facebook test, the data was used to train neural networks used for existing chatbots, with the results then assessed by another group of Mechanical Turkers.

In each case, they were asked to conduct a conversation with the persona-driven bot, and compare it with both other chatbots and humans.

The persona bot didn't score as highly on criteria like "fluency" and "consistency" as the humans but it outperformed the chatbot trained on movie dialogue.

The new test is significant after Facebook last year had to shut down one of its AI systems after chatbots started speaking in their own language defying the codes provided.

The FAIR team found that while they were busy trying to improve chatbots, the "dialogue agents" were creating their own language.

Soon, the bots began to deviate from the scripted norms and started communicating in an entirely new language which they created without human input.

Using Machine Learning (ML) algorithms, the "dialogue agents" were left to converse freely in an attempt to strengthen their conversational skills.

The researchers also found these bots to be "incredibly crafty negotiators".

Show Full Article
TAGS:
Next Story