Why humans can't use natural language processing to speak with the animals
Why humans can't use natural language processing to speak with the animals
We’ve already got machine-learning and NLP that can translate speech into any number of languages.
I love that instead of using an image of one of a million types of animals living atm, they chose to put a picture of Animal.. of course we can't communicate with Animal, he's above our intellectual level.
What about with dolphins, though? Most other animals don't actually have enough of a repitiore of patterns to figure out a lot of things they might be saying, but dolphins have been shown to have speech patterns in their calls so similar to all human languages, it's hard not to think they have some kind of actual language.
Dolphins, whales, apes, bats, elephants and prairie dogs would be good candidates. For most species however, since their repertoire of communication is quite limited, attempting communication wouldn't be likely to succeed.
https://en.wikipedia.org/wiki/Animal_language
Prairie dogs, being a species well accessible by humans (they live in fixed underground "settlements", don't swim or fly where people cannot record them, and aren't dangerous to approach) have been studied to an extent, and their language does have semantics:
Their calls transmit semantic information, which was demonstrated when playbacks of alarm calls in the absence of predators led to escape behavior appropriate for the types of predators associated with the calls. The alarm calls also contain descriptive information about the general size, color, and speed of the predator.[25]
I imagine that prairie dogs are already capable of coming up with statements like "big cat coming slowly from north", so maybe some of their colonies, in the right conditions, develop more complex language. Since they don't travel much, each of their colonies might have a different language, however.
Perhaps the most interesting language would be that of squids:
In addition to camouflage and appearing larger in the face of a threat, squid use color, patterns, and flashing to communicate with one another in various courtship rituals. Caribbean reef squid can send one message via color patterns to a squid on their right, while they send another message to a squid on their left.[38][39]
This is the best summary I could come up with:
Natural Language Programming (NLP) is the branch of AI that enables computers and algorithmic models to interpret text and speech, including the speaker’s intent, the same way we meatsacks do.
The field of NLP research has undergone a significant evolution in recent years, as its core systems have migrated from older Recurrent and Convoluted Neural Networks towards Google’s Transformer architecture, which greatly increases training efficiency.
Having a large corpus of data to work with in this situation also enables unsupervised learning techniques to be used to “extract the latent conceptual space,” Dr. Goodman said, though that method is more resource intensive and less efficient.
“For most human languages we assume the [quartet concepts] are kind of, sort of similar, like, maybe they don't have ‘king and queen’ but they definitely have ‘man and woman,’” Dr. Goodman continued.
And without even that rudimentary conceptual alignment to work from, discerning the context and intent of a animal’s call — much less, deciphering the syntax, grammar and semantics of the underlying communication system — becomes much more difficult.
Biologging tags — animal-borne sensors affixed to hide, hair, or horn that track the locations and conditions of their hosts — continue to shrink in size while growing in both capacity and capability, which should help researchers gather even more data about these communities.
I'm a bot and I'm open source!