Structural Tags, Annealing and Automatic Word Classification

dc.creatorMcMahon, John
dc.creatorSmith, F. J.
dc.date1994-05-30
dc.date.accessioned2026-07-07T09:09:17Z
dc.date.available2026-07-07T09:09:17Z
dc.descriptionThis paper describes an automatic word classification system which uses a locally optimal annealing algorithm and average class mutual information. A new word-class representation, the structural tag is introduced and its advantages for use in statistical language modelling are presented. A summary of some results with the one million word LOB corpus is given; the algorithm is also shown to discover the vowel-consonant distinction and displays an ability to cluster words syntactically in a Latin corpus. Finally, a comparison is made between the current classification system and several leading alternative systems, which shows that the current system performs respectably well.
dc.description14 Page Paper. PostScript File
dc.identifierhttps://arxiv.org/abs/cmp-lg/9405029
dc.identifierhttp://arxiv.org/abs/cmp-lg/9405029
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/150980
dc.subjectComputation and Language
dc.titleStructural Tags, Annealing and Automatic Word Classification
dc.typetext

Files

Collections