Memory-Based Language Processing
Memory-based language processing--a machine learning and problem solving method for language technology--is based on the idea that the direct re-use of examples using analogical reasoning is more suited for solving language processing problems than the application of rules extracted from those examples. This book discusses the theory and practice of memory-based language processing, showing its comparative strengths over alternative methods of language modelling. Language is complex, with few generalizations, many sub-regularities and exceptions, and the advantage of memory-based language processing is that it does not abstract away from this valuable low-frequency information.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
abstraction accuracy algorithm ambitag attachment Bosch Buchholz CELEX-2 chapter CHUNK class label compression Computational Linguistics context Daelemans data set decision tree default DIMIN disambiguation displays distance Dutch editing error reduction examples in memory experiments F-score FAMBL family expressions fc-NN feature values feature weighting Figure gain ratio German plural gplural.train HAPAX-0 hyperrectangle IBl's IGTREE input lazy learning learning algorithm learning methods letter-phoneme letters lexical lexicon machine learning mapping match memory-based language processing memory-based learning metric models MORPH morphemes morphological analysis MVDM n-grams natural language processing nearest neighbors NLP tasks nodes noun part-of-speech tags performance phonemization phrase chunking POS tagging predicted problem relevance represented RIPPER rule induction segmentation sentence sequence shallow parsing similar stacking statistical syntactic Table tagger test data test set Timbl TlMBL training data training examples training set treebank trigrams University of Antwerp unknown words verb window word phonemization wordform Zavrel