Haoran Xu

BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation

2021 · arXiv (Cornell University)

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems. However, …

Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations

2022 · arXiv (Cornell University)

We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset …