We present two axiomatic and three conjectural conditions which a model inducing natural language categories should dispose of, if ever it aims to be considered as "cognitively plausible". 1st axiomatic condition is that the model should involve a bootstrapping component. 2nd axiomatic condition is that it should be data-driven. 1st conjectural condition demands that the model integrates the surface features - related to prosody, phonology and morphology - somewhat more intensively than is the case in existing Markov-inspired models. 2nd conjectural condition demands that asides integrating symbolic and connectionist aspects, the model under question should exploit the global geometric and topologic properties of vector-spaces upon which it operates. At last we shall argue that model should facilitate qualitative evaluation, for example in form of a POS-i oriented Turing Test. In order to support our claims, we shall present a POS-induction model based on trivial k-way clustering of vectors representing suffixal and co-occurrence information present in parts of Multext-East corpus. Even in very initial stages of its development, the model succeeds to outperform some more complex probabilistic POS-induction models for lesser computational cost. © Springer International Publishing Switzerland 2014.
CITATION STYLE
Hromada, D. D. (2014). Conditions for Cognitive Plausibility of Computational Models of Category Induction. In Communications in Computer and Information Science (Vol. 443 CCIS, pp. 93–105). Springer Verlag. https://doi.org/10.1007/978-3-319-08855-6_11
Mendeley helps you to discover research relevant for your work.