Jacob Parnell

reward function (3) reinforcement learning (3) neural machine translation (2) contextual embedding (2) abstractive summarisation (2) reward design (1) gradient estimator (1) training objective (1) abstractive summarization (1) multi-document summarization (1) multilingual language model (1) bert score (1) few-shot fine-tuning (1) cross-lingual summarization (1) rouge score (1) differentiable pipeline (1) negative log-likelihood (1) text summarisation (1) reinforcement learning reward (1) rouge scoring (1)