Do Not Forget: Full Memory in Memory-Based Learning of Word Pronunciation

Memory based learning keeping full memory of learning material appears a viable approach to learning nlp tasks and is often superior in generalisation accuracy to eager learning approaches that abstract from learning mate rial Here we investigate three partial memory based learning approaches which remove from memory speci c task instance types estimated to be exceptional The three approaches each implement one heuristic function for estimat ing exceptionality of instance types i typi cality ii class prediction strength and iii friendly neighbourhood size Experiments are performed with the memory based learning al gorithm ib ig trained on English word pro nunciation We nd that removing instance types with low prediction strength ii is the only tested method which does not seriously harm generalisation accuracy We conclude that keeping full memory of types rather than tokens and excluding minority ambiguities ap pear to be the only performance preserving op timisations of memory based learning