Broad-coverage parsing using human-like memory constraints

William Schuler, Samir AbdelRahman, Tim Miller, Lane Schwartz

Research output: Contribution to journalArticlepeer-review


Human syntactic processing shows many signs of taking place within a general-purpose short-term memory. But this kind of memory is known to have a severely constrained storage capacity - possibly constrained to as few as three or four distinct elements. This article describes a model of syntactic processing that operates successfully within these severe constraints, by recognizing constituents in a right-corner transformed representation (a variant of left-corner parsing)and mapping this representation to random variables in a Hierarchical Hidden Markov Model, a factored time-series model which probabilistically models the contents of a bounded memory store over time. Evaluations of the coverage of this model on a large syntactically annotated corpus of English sentences, and the accuracy of a bounded-memory parsing strategy based on this model, suggest this model may be cognitively plausible.

Original languageEnglish (US)
Pages (from-to)1-30
Number of pages30
JournalComputational Linguistics
Issue number1
StatePublished - Mar 2010
Externally publishedYes

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Computer Science Applications
  • Artificial Intelligence


Dive into the research topics of 'Broad-coverage parsing using human-like memory constraints'. Together they form a unique fingerprint.

Cite this