I am a Research Scientist at
Facebook AI Research in Menlo Park, CA and I work on machine learning and natural language processing.
I earned my Ph.D. at the University of Edinburgh for my work on syntactic
parsing with approximate inference.
- Our papers on Depth-Adaptive Transformers and vq-wav2vec have been accepted to ICLR 2020.
- I recently gave a talk at the Workshop on Neural Generation and Translation on efficient sequence modeling.
- All of our submissions to WMT'19 were ranked top in the human evaluation. Read our systems paper, the blog post and download the models.
- Our paper on wav2vec shows that self-supervised learning can improve actual speech recognition. Also read the blog post.
- We released a new dataset on long form question answering, read the paper, the blog post and download the dataset.