2019/07/12 XLNet: Generalized Autoregressive Pretraining for Language Understanding

2019-07-12T14:00:00Z session topic is XLNet: Generalized Autoregressive Pretraining for Language Understanding. Here is the abstract of the paper:

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment analysis, and document ranking.

:writing_hand: We take notes and prepare the discussion in a public GDoc, you are very welcome to ask questions or share your thoughts in it

:clock4: The session lasts for one hour between 2019-07-12T14:00:00Z and 2019-07-12T15:00:00Z

:world_map: The reading club happens on-line on zoom or in source{d} office in Madrid

:information_source: For more details, see our repository on GitHub