The segmentation problem in morphology learning

Recently there has been a large literature on various approaches to learning morphology, and the success and cognitive plausibility of different approaches (Rumelhart and McClelland (1986), MacWhinney and Leinbach (1991) arguing for connectionist models, Pinker and Prince (1988), Lachter and Bever (1988), Marcus et al. (1992) arguing against connectionist models, Ling and Marinov (1993), Ling (1994) using ID3/C4.5 decision trees, and Mooney and Califf (1995, 1996) using inductive logic programming/decision lists, among others). However except for a couple of forays into German this literature has been exclusively concerned with the learning of the English past tense. This has not worried some. Ling is happy to describe it as "a landmark task". But while the English past tense has some interesting features in its combination of regular rules with semi-productive strong verb patterns, it is in many other respects a very trivial morphological system reflecting the generally vestigal nature of inflectional morphology within modem English.