2020

BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT

Kao, Wei-Tsung, Wu, Tsung-Han, Chi, Po-Han et al.

Understand

Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box.

  • A variety of previous works have tried to lift the veil of BERT and understand each layer's functionality.
  • In this paper, we found that surprisingly the output layer of BERT can reconstruct the input sentence by directly taking each layer of BERT as input, even though the output layer has never seen the input other than the final hidden layer.
  • This fact remains true across a wide variety of BERT-based models, even when some layers are duplicated.

Built on

Similar

  • Attention is all you need

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017 · 2017

    Cited alongside, same era.

  • Deep contextualized word representations

    Original

    Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018 · 2018

    Cited alongside, same era.

  • Know what you don’t know: Unanswerable questions for SQuAD

    Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018 · 2018

    Cited alongside, same era.

  • Glue: A multi-task benchmark and analysis platform for natural language understanding

    Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018 · 2018

    Cited alongside, same era.

  • BERT rediscovers the classical NLP pipeline

    Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019a

    Cited in the paper.

Then

  • On identifiability in transformers

    Original

    Gino Brunner, Yang Liu, Damián Pascual, Oliver Richter, Massimiliano Ciaramita, and Roger Wattenhofer. 2019 · 2019

    Later among the works it cites.

  • BERT: Pre-training of deep bidirectional transformers for language understanding

    Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019 · 2019

    Later among the works it cites.

  • Designing and interpreting probes with control tasks

    John Hewitt and Percy Liang. 2019 · 2019

    Later among the works it cites.

  • A structural probe for finding syntax in word representations

    John Hewitt and Christopher D Manning. 2019 · 2019

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…