Forgetting Exceptions is Harmful in Language Learning

dc.creatorDaelemans, Walter
dc.creatorBosch, Antal van den
dc.creatorZavrel, Jakub
dc.date1998-12-22
dc.date.accessioned2026-07-07T03:23:53Z
dc.date.available2026-07-07T03:23:53Z
dc.descriptionWe show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural language processing tasks: grapheme-to-phoneme conversion, part-of-speech tagging, prepositional-phrase attachment, and base noun phrase chunking. In a first series of experiments we combine memory-based learning with training set editing techniques, in which instances are edited based on their typicality and class prediction strength. Results show that editing exceptional instances (with low typicality or low class prediction strength) tends to harm generalization accuracy. In a second series of experiments we compare memory-based learning and decision-tree learning methods on the same selection of tasks, and find that decision-tree learning often performs worse than memory-based learning. Moreover, the decrease in performance can be linked to the degree of abstraction from exceptions (i.e., pruning or eagerness). We provide explanations for both results in terms of the properties of the natural language processing tasks and the learning algorithms.
dc.description31 pages, 7 figures, 10 tables. uses 11pt, fullname, a4wide tex styles. Pre-print version of article to appear in Machine Learning 11:1-3, Special Issue on Natural Language Learning. Figures on page 22 slightly compressed to avoid page overload
dc.identifierhttps://arxiv.org/abs/cs/9812021
dc.identifierhttp://arxiv.org/abs/cs/9812021
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33121
dc.subjectComputation and Language
dc.subjectMachine Learning
dc.subjectI.2.6; I.2.7
dc.titleForgetting Exceptions is Harmful in Language Learning
dc.typetext

Files

Collections