/* ---- Google Analytics Code Below */

Wednesday, May 20, 2020

Can AI tell Moral right from Wrong?

As suggested moral choices have much to do with context, and are hard to extract from just words.    I like that changes over time are being considered.  Time is often the most important metadata, and infers the trajectories of choices being made.   We did something similar when seeking to understand the future of marketing messages in context.

Scientists claim they can teach AI to judge ‘right’ from ‘wrong’
The moral machine shows how moral values change over time
Story By  Thomas Macaulay in NextWeb

Scientists claim they can “teach” an AI moral reasoning by training it to extract ideas of right and wrong from texts.

Researchers from Darmstadt University of Technology (DUT) in Germany fed their model books, news, and religious literature so it could learn the associations between different words and sentences. After training the system, they say it adopted the values of the texts.

As the team put it in their research paper:

The resulting model, called the Moral Choice Machine (MCM), calculates the bias score on a sentence level using embeddings of the Universal Sentence Encoder since the moral value of an action to be taken depends on its context.

This allows the system to understand contextual information by analyzing entire sentences rather than specific words. As a result, the AI could work out that it was objectionable to kill living beings, but fine to just kill time.   ... "

No comments: