The emergence of number and syntax units in LSTM language models

Abstract

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.

To appear in Proceedings of NAACL, Minneapolis, MN, 2019

References in corpus (1)

• From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning

Cited by in corpus (4)

• Can RNNs learn Recursive Nested Subject-Verb Agreements?
• Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
• Word Interdependence Exposes How LSTMs Compose Representations
• Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?