Paper: Toward a Psycholinguistically-Motivated Model of Language Processing

ACL ID C08-1099
Title Toward a Psycholinguistically-Motivated Model of Language Processing
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2008
Authors

Psycholinguistic studies suggest a model of human language processing that 1) per- forms incremental interpretation of spo- ken utterances or written text, 2) preserves ambiguity by maintaining competing anal- yses in parallel, and 3) operates within a severely constrained short-term memory store — possibly constrained to as few as four distinct elements. This paper de- scribes a relatively simple model of lan- guage as a factored statistical time-series process that meets all three of the above desiderata; and presents corpus evidence that this model is sufficient to parse natu- rally occurring sentences using human-like bounds on memory.