Search Results for author:
Found 2 papers, 1 papers with code
Scaffolded input promotes atomic organization in the recurrent neural network language model
We conceptualize this limitation of the RNN as a failure to learn atomic internal states - states which capture information relevant to single word types without being influenced by redundant information provided by words with which they co-occur.
BabyBERTa: Learning More Grammar With Small-Scale Child-Directed Language
Transformer-based language models have taken the NLP world by storm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
