Memory‐Based Learning

Daelemans, Walter; Bosch, Antal van den

doi:10.1002/9781444324044.ch6

Cited by 15 publications

(11 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In fact, however, this is also the case for many exemplar models (e.g. Daelemans & van den Bosch, 2010, TiMBL; Regier, 2005, LEX; many versions of the GCM), which use attentional feature weights to learn to preferentially weight the cues that best discriminate different outcomes, in a manner identical to discriminative learning models. Consequently, a difference between the approaches can be seen only when we consider ‘pure’ exemplar models that do not posit feature weights (e.g.…”

Section: Resultsmentioning

confidence: 99%

“…The Tilburg Memory Based Learner (TiMBL; Daelemans & van den Bosch, 2010; Keuleers, 2008) is similar in its use of a form of feature weighting (information gain) and a decay function. It differs in that it considers not all stored exemplars, just k nearest neighbours (set as a model parameter) and, in most implementations, does not represent token frequency in any way (though the English past-tense model of Van Noord & Spenader, 2015, is an exception).…”

Section: Morphologically Inflected Wordsmentioning

confidence: 99%

See 1 more Smart Citation

Against stored abstractions: A radical exemplar model of language acquisition

Ambridge

2019

First Language

115

View full text Add to dashboard Cite

The goal of this article is to make the case for a radical exemplar account of child language acquisition, under which unwitnessed forms are produced and comprehended by on-the-fly analogy across multiple stored exemplars, weighted by their degree of similarity to the target with regard to the task at hand. Across the domains of (1) word meanings, (2) morphologically inflected words, (3) n-grams, (4) sentence-level constructions and (5) phonetics and phonology, accounts based on independently-represented abstractions (whether formal rules or prototype categories) fail for two reasons. First, it is not possible to posit abstractions that delineate possible and impossible form; e.g. that (1) rule in pool tables and data tables, but rule out chairs, (2) rule in the past-tense forms netted and bet but rule out * setted and * jet, (3) rule in the bigram f+t but rule out (probabilistically) v+t, (4) rule in both John feared Bill and John frightened Bill but rule out * John laughed Bill, (5) rule in Speaker A but rule out Speaker B as the person who produced a particular word (e.g. Sa’urday). Second, for each domain, empirical data provide evidence of exemplar storage that cannot be captured by putative abstractions: e.g. speakers prefer and/or show an advantage for (1) exemplar variation even within word-meaning ‘category boundaries’, (2) novel inflected forms that are similar to existing exemplars, (3) n-grams that have occurred frequently in the input, (4) SVO sentences with he as SUBJECT and it as OBJECT and (5) repeated productions of ‘the same’ word that are phonologically similar or, better still, identical. An exemplar account avoids an intractable lumping-or-splitting dilemma facing abstraction-based accounts and provides a unitary explanation of language acquisition across all domains; one that is consistent with models and empirical findings from the computational modelling and neuroimaging literature.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Morphologically Inflected Wordsmentioning

confidence: 99%

Against stored abstractions: A radical exemplar model of language acquisition

Ambridge

2019

First Language

115

View full text Add to dashboard Cite

show abstract

“…In other work we and others have shown that memory-based learning offers competitive state-of-the-art performance, so that it can be used in most practical natural language processing situations in lieu of any other state-of-the-art machine-learning algorithm (for an overview, see Daelemans and Van den Bosch, 2009). …”

Section: How Friendly Are Linguistic Neighbourhoods?mentioning

confidence: 97%

“…In sum, through experimentation we have shown that although Saussurean analogical reasoning, a form of selective abductive reasoning, has no built-in safety measures to avoid erroneous outcomes, MBLP can offer good performance on unseen data in many natural language processing tasks by using the principle directly, offering the best possible performance when all of the training data is retained in memory. In other work we and others have shown that memory-based learning offers competitive state-of-the-art performance, so that it can be used in most practical natural language processing situations in lieu of any other state-of-the-art machine-learning algorithm (for an overview, see Daelemans and Van den Bosch, 2009).…”

Section: How Friendly Are Linguistic Neighbourhoods?mentioning

confidence: 99%

Implicit Schemata and Categories in Memory-based Language Processing

Bosch

Daelemans

2013

Lang Speech

Self Cite

View full text Add to dashboard Cite

Memory-based language processing (MBLP) is an approach to language processing based on exemplar storage during learning and analogical reasoning during processing. From a cognitive perspective, the approach is attractive as a model for human language processing because it does not make any assumptions about the way abstractions are shaped, nor any a priori distinction between regular and exceptional exemplars, allowing it to explain fluidity of linguistic categories, and both regularization and irregularization in processing. Schema-like behaviour and the emergence of categories can be explained in MBLP as by-products of analogical reasoning over exemplars in memory. We focus on the reliance of MBLP on local (versus global) estimation, which is a relatively poorly understood but unique characteristic that separates the memory-based approach from globally abstracting approaches in how the model deals with redundancy and parsimony. We compare our model to related analogy-based methods, as well as to example-based frameworks that assume some systemic form of abstraction.

show abstract

“…Frog was originally developed for Dutch and integrates several NLP modules that perform word and sentence boundary detection, POS tag and lemma labeling, named entity recognition and morphological and syntactic analysis. e majority of the modules are based on memory-based machine learning algorithms [6], a technique proposed to learn NLP classi cation problems with as its de ning characteristic that it stores in memory all available instances of a task, and that it extrapolates from the most similar instances in memory to deal with unseen cases.…”

Section: Frogmentioning

confidence: 99%

A Memory-Based Lemmatizer for Ancient Greek

Bary

Berck

Hendrickx

2017

Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage

View full text Add to dashboard Cite

In this paper we present the lemmatizer that we developed for Ancient Greek: GLEM. As far as we know, GLEM is the rst publicly available lemmatizer for Ancient Greek that uses POS information to disambiguate and that also assigns output to unseen words, words that are not yet in the lexicon. As the basis for the lemmatizer we used an existing memorybased learning tool, Frog, that was originally developed for Dutch and that we converted to work for Ancient Greek. As the results of Frog on Ancient Greek were rather modest, we used Frog to create a smarter lemmatizer, GLEM, that uses a lexicon look up in addition to the memory-based tool Frog. We evaluate and compare the performance of GLEM against the Frog lemmatizer and the already existing CLTK lemmatizer and observe that GLEM achieves the highest accuracy of 93% on an unseen test corpus sample. GLEM's look up component overcomes the di culty of a relative small training set in combination with a morphologically rich language, while the memory-based learning component enables GLEM to handle unknown words.

show abstract

Memory‐Based Learning

Cited by 15 publications

References 91 publications

Against stored abstractions: A radical exemplar model of language acquisition

Against stored abstractions: A radical exemplar model of language acquisition

Implicit Schemata and Categories in Memory-based Language Processing

A Memory-Based Lemmatizer for Ancient Greek

Contact Info

Product

Resources

About