The emergence of number and syntax units in LSTM language models

By Yair Lakretz, Germán Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, Marco Baroni. 2019

190 citations recorded by the source corpus.

Recent work has shown that LSTMs trained on a generic language modeling objective capture syntax-sensitive generalizations such as long-distance number agreement. We have however no mechanistic understanding of how they accomplish this remarkable feat. Some have conjectured it depends on heuristics that do not truly take hierarchical structure into account. We present here a detailed study of the inner mechanics of number tracking in LSTMs at the single neuron level. We discover that long-distance number information is largely managed by two “number units”. Importantly, the behaviour of these units is partially controlled by other units independently shown to track syntactic structure. We conclude that LSTMs are, to some extent, implementing genuinely syntactic processing mechanisms, paving the way to a more general understanding of grammatical encoding in LSTMs.

Subfields: Artificial Intelligence, Natural Language Processing, Computational Linguistics & Semantics

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. Yoav Goldberg
  4. Percy Liang
  5. Luke S. Zettlemoyer
  6. Douwe Kiela
  7. Samuel R. Bowman
  8. Christopher D. Manning

In Natural Language Processing

  1. Yonatan Belinkov
  2. Yoav Goldberg
  3. Mohit Bansal
  4. Douwe Kiela
  5. Samuel R. Bowman
  6. James R. Glass
  7. Tal Linzen
  8. Percy Liang

In Computational Linguistics & Semantics

  1. Yonatan Belinkov
  2. Yoav Goldberg
  3. Tal Linzen
  4. Dieuwke Hupkes
  5. Willem H. Zuidema
  6. Ivan Titov
  7. Douwe Kiela
  8. James R. Glass

Citations in the corpus