The resolution of "it" should not be based on the probability but meaning of the sentence. Something that Vicki can do. #VickiIsHere
Another example of pronoun resolution based on meaning:
"John gave an apple to Jeff because he was hungry and he had an extra one."
We show large language models trained on massive text corpora (LM1b, CommonCrawl, Gutenberg) can be used for commonsense reasoning and obtain SOTA on Winograd Schema Challenge. Paper at http://arxiv.org/abs/1806.02847 , results reproducible at https://git.io/vhaaf pic.twitter.com/s3uyrksAQz
-
Tweet je nedostupan.
-
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Nice example of a distribution over counterfactuals!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Great stuff! And thanks for sharing the trained model,
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
What happens when the trophy doesn't look good in the suitcase because it's too small?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
Tweet je nedostupan.
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.