Tree (set theory)

Neuroscience

Beam search

Mathematics

Mathematical physics

Rule-based machine translation

Syntax

Variety (cybernetics)

Recurrent neural network

Search algorithm

String (physics)

Mathematical analysis

Cognition

Artificial intelligence

Psychology

N400

Parsing

Programming language

Natural language processing

Contrast (vision)

Computer science

Event-related potential

Speech recognition

Generative grammar

Artificial neural network

Prosody

P600

Recurrent neural network grammars (RNNGs) are generative models of (tree , string ) pairs that rely on neural networks to evaluate derivational choices. Parsing with them using beam search yields a variety of incremental complexity metrics such as word surprisal and parser action count. When used as regressors against human electrophysiological responses to naturalistic text, they derive two amplitude effects: an early peak and a P600-like later peak. By contrast, a non-syntactic neural language model yields no reliable effects. Model comparisons attribute the early peak to syntactic composition within the RNNG. This pattern of results recommends the RNNG+beam search combination as a mechanistic model of the syntactic processing that occurs during normal human language comprehension.

Finding syntax in human encephalography with beam search