1. Language models are unsupervised multitask learners;radford;OpenAIRE blog,2019
2. Bert: Pre-training of deep bidirectional transformers for language understanding;devlin;Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol,2019
3. ParseNet: Looking wider to see better;liu;arXiv 1506 04579,2015
4. Fast approximate energy minimization via graph cuts
5. Statistical region merging