1 code implementation • 16 Mar 2024 • Sai Prasanna, Karim Farid, Raghu Rajan, André Biedenkapp
Toward the goal of ZSG to unseen variation in context, we propose the contextual recurrent state-space model (cRSSM), which introduces changes to the world model of the Dreamer (v3) (Hafner et al., 2023).
no code implementations • EMNLP 2020 • Sai Prasanna, Anna Rogers, Anna Rumshisky
Large Transformer-based models were shown to be reducible to a smaller number of self-attention heads and layers.
1 code implementation • SEMEVAL 2019 • Sai Prasanna, Sri Ananda Seelan
This paper describes our submission for the SemEval-2019 Suggestion Mining task.