Identifying and Controlling Important Neurons in Neural Machine Translation

By Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James R. Glass. 2018

198 citations recorded by the source corpus.

Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individual neurons. We develop unsupervised methods for discovering important neurons in NMT models. Our methods rely on the intuition that different models learn similar properties, and do not require any costly external supervision. We show experimentally that translation quality depends on the discovered neurons, and find that many of them capture common linguistic phenomena. Finally, we show how to control NMT translations in predictable ways, by modifying activations of individual neurons.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yonatan Belinkov
  2. Mohit Bansal
  3. Graham Neubig
  4. Yoav Goldberg
  5. Luke S. Zettlemoyer
  6. Percy Liang
  7. Kyunghyun Cho
  8. Felix Stahlberg

In Computer Vision and Pattern Recognition

  1. Yonatan Belinkov
  2. Felix Stahlberg
  3. Luc Van Gool
  4. Dacheng Tao
  5. Trevor Darrell
  6. Mohit Bansal
  7. Xiaogang Wang
  8. Andrew Zisserman

In Natural Language Processing

  1. Yonatan Belinkov
  2. Felix Stahlberg
  3. Graham Neubig
  4. Yoav Goldberg
  5. James R. Glass
  6. Mohit Bansal
  7. Kyunghyun Cho
  8. Samuel R. Bowman

In Machine Translation

  1. Yonatan Belinkov
  2. Jesse Vig
  3. Nadir Durrani
  4. Hassan Sajjad
  5. Fahim Dalvi
  6. James R. Glass
  7. Ivan Titov
  8. Elena Voita

Citations in the corpus