Abstract | ||
---|---|---|
Psycholinguistic studies suggest a model of human language processing that 1) performs incremental interpretation of spoken utterances or written text, 2) preserves ambiguity by maintaining competing analyses in parallel, and 3) operates within a severely constrained short-term memory store --- possibly constrained to as few as four distinct elements. This paper describes a relatively simple model of language 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 naturally occurring sentences using human-like bounds on memory. |
Year | Venue | Keywords |
---|---|---|
2008 | COLING | distinct element,factored statistical time-series process,human-like bound,simple model,human language processing,incremental interpretation,corpus evidence,short-term memory store,written text,psycholinguistic study,psycholinguistically-motivated model,time series,short term memory |
Field | DocType | Citations |
Computer science,Speech recognition,Natural language processing,Artificial intelligence,Parsing,Ambiguity | Conference | 8 |
PageRank | References | Authors |
0.88 | 10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
William Schuler | 1 | 125 | 17.78 |
Tim Miller | 2 | 63 | 8.17 |
Samir AbdelRahman | 3 | 88 | 9.54 |
Lane Schwartz | 4 | 209 | 18.01 |