Machine learning of morphological rules by generalization and analogy

Wothke, Klaus

doi:10.3115/991365.991450

Cited by 6 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The properties (2), (3), and (4) are the same as in Kaplan et al [5], but XMAS has in addition the properties (5)- (9). XMAS shares the properties ( 3) and ( 7) with Wothke [15], but is…”

Section: Related Work and Concluding Remarksmentioning

confidence: 92%

Morphological analysis and synthesis by automated discovery and acquisition of linguistic rules

Byoung-Tak

Kim

1990

Proceedings of the 13th Conference on Computational Linguistics -

View full text Add to dashboard Cite

':[his paper describes a rule-based machine learning approach to morphological processing in the system called XMAS. XMAS discovers and acquires linguistic rules from examples of morphological combinations and accomplishes the morphological analysis and synthesis by applying the rules. This approach is independent of languages, saves time and effort for development and maintenance, and takes small lexicon space. A Korean version of XMAS is effectively working in the English-Korean machine translation system KSHALT.

show abstract

“…The properties (2), (3), and (4) are the same as in Kaplan et al [5], but XMAS has in addition the properties (5)- (9). XMAS shares the properties ( 3) and ( 7) with Wothke [15], but is…”

Section: Related Work and Concluding Remarksmentioning

confidence: 92%

Morphological analysis and synthesis by automated discovery and acquisition of linguistic rules

Byoung-Tak

Kim

1990

Proceedings of the 13th Conference on Computational Linguistics -

View full text Add to dashboard Cite

show abstract

“…For example, the input to a past tense learner could be word pairs such as (in orthography) (walk, walked), (beat, beat), (eat, ate), etc. "Past tense" models of learning and processing have been a topic of strong interest in cognitive science (Rumelhart and McClelland 1986;Pinker and Prince 1988;Pinker 1999;Pinker and Ullmann 2002;McClelland and Patterson 2002), and many learning systems have been developed for this problem (Golding and Thompson 1985;Rumelhart and McClelland 1986;Wothke 1986;Ling 1994;Daelemans et al 1996;Mooney and Califf 1996;Molnar 2001;Clark 2001Clark , 2002Albright and Hayes 2002).…”

Section: Supervised Inflection Learning Modelsmentioning

confidence: 99%

Investigating the Relationship Between Linguistic Representation and Computation through an Unsupervised Model of Human Morphology Learning

Chan

Lignos

2010

Res on Lang and Comput

View full text Add to dashboard Cite

We develop an unsupervised algorithm for morphological acquisition to investigate the relationship between linguistic representation, data statistics, and learning algorithms. We model the phenomenon that children acquire the morphological inflections of a language monotonically by introducing an algorithm that uses a bootstrapped, frequency-driven learning procedure to acquire rules monotonically. The algorithm learns a morphological grammar in terms of a Base and Transforms representation, a simple rule-based model of morphology. When tested on corpora of child-directed speech in English from CHILDES (MacWhinney in The CHILDESProject: Tools for analyzing talk. Erlbaum, Hillsdale, 2000), the algorithm learns the most salient rules of English morphology and the order of acquisition is similar to that of children as observed by Brown (A first language: the early stages. Harvard University Press, Cambridge, 1973). Investigations of statistical distributions in corpora reveal that the algorithm is able to acquire morphological grammars due to its exploitation of Zipfian distributions in morphology through type-frequency statistics. These investigations suggest that the computation and frequency-driven selection of discrete morphological rules may be important factors in children's acquisition of basic inflectional morphological systems.

show abstract

“…A very different, more practically oriented, motivation for ULM came in the 1980s, beginning with the supervised morphology learning ideas by Wothke (1985Wothke ( , 1986 and Klenk (1985aKlenk ( , 1985b which later led to partly unsupervised methods (see the following). Because full natural language lexica, at the time, were too big to fit in working memory, these authors were looking for a way to analyze or stem running words in a "nichtlexikalisches" manner, that is, without the storage and use of a large lexicon.…”

Section: History and Motivation Of Ulmmentioning

confidence: 99%

Unsupervised Learning of Morphology

Hammarström

Borin

2011

Computational Linguistics

View full text Add to dashboard Cite

This article surveys work on Unsupervised Learning of Morphology. We define Unsupervised Learning of Morphology as the problem of inducing a description (of some kind, even if only morpheme-segmentation) of how orthographic words are built up given only raw text data of a language. We briefly go through the history and motivation of the this problem. Next, over 200 items of work are listed with a brief characterization, and the most important ideas in the field are critically discussed. We summarize the achievements so far and give pointers for future developments.

show abstract

Machine learning of morphological rules by generalization and analogy

Cited by 6 publications

References 2 publications

Morphological analysis and synthesis by automated discovery and acquisition of linguistic rules

Morphological analysis and synthesis by automated discovery and acquisition of linguistic rules

Investigating the Relationship Between Linguistic Representation and Computation through an Unsupervised Model of Human Morphology Learning

Unsupervised Learning of Morphology

Contact Info

Product

Resources

About