Memory-Based Language Processing
Cambridge University Press, Sep 1, 2005 - Language Arts & Disciplines
Memory-based language processing - a machine learning and problem solving method for language technology - is based on the idea that the direct reuse 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. By applying the model to a range of benchmark problems, the authors show that for linguistic areas ranging from phonology to semantics, it produces excellent results. They also describe TiMBL, a software package for memory-based language processing. The first comprehensive overview of the approach, this book will be invaluable for computational linguists, psycholinguists and language engineers.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Chapter 2 Inspirations from linguistics and artificial intelligence
Chapter 3 Memory and Similarity
Chapter 4 Application to morphophonology
Chapter 5 Application to shallow parsing
Other editions - View all
abstraction accuracy algorithm ambitag artificial intelligence attachment Bosch Buchholz CELEX-2 chapter CHUNK class label compression Computational Linguistics context corpus Daelemans data set decision tree default DIMIN disambiguation distance Dutch editing error reduction examples in memory experiments F-score FAMBL family expressions feature values feature weighting Figure focus gain ratio German plural HAPAX-0 hyperrectangle IGTREE input language learning lazy learning learning algorithm learning methods 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 parameter part-of-speech tags performance phonemization phrase chunking POS tagging predicted problem Proceedings represented RIPPER rule induction segmentation sequence shallow parsing similar Skousen stacking statistical syntactic Table tagger test data test set Tilburg TIMBL Tjong Kim Sang training data training examples training set Treebank TRIBL trigrams unknown words verb word phonemization wordform Zavrel