Investigating representations of verb bias in neural language models
EMNLP 2020, pp. 4653-4663, 2020.
We found that transformer architectures corresponded especially well with human verb bias judgments
Languages typically provide more than one grammatical construction to express certain types of messages. A speaker’s choice of construction is known to depend on multiple factors, including the choice of main verb – a phenomenon known as verb bias. Here we introduce DAIS, a large benchmark dataset containing 50K human judgments for 5K dis...More
PPT (Upload PPT)