By Hinrich Schütze

This quantity is anxious with how ambiguity and ambiguity answer are discovered, that's, with the purchase of the various representations of ambiguous linguistic types and the information worthy for choosing between them in context. Schütze concentrates on how the purchase of ambiguity is feasible in precept and demonstrates that specific forms of algorithms and studying architectures (such as unsupervised clustering and neural networks) can be successful on the activity. 3 forms of lexical ambiguity are taken care of: ambiguity in syntactic categorisation, semantic categorisation, and verbal subcategorisation. the amount offers 3 varied types of ambiguity acquisition: Tag area, note area, and Subcat Learner, and addresses the significance of ambiguity in linguistic illustration and its relevance for linguistic innateness.

Show description

Read Online or Download Ambiguity Resolution in Language Learning: Computational and Cognitive Models PDF

Similar semantics books

Lexical-Semantic Relations: Theoretical and practical perspectives (Lingvisticæ Investigationes Supplementa)

This selection of articles sketches the complexity of the topic of lexical-semantic family members and addresses semantic, lexicographic and computational concerns on an array of that means kin in numerous languages. It brings jointly a number of linguistic reviews at the contextualised building of synonymy and antonymy in discourse.

Code Biology: A New Science of Life

This e-book is the research of all codes of lifestyles with the traditional tools of technological know-how. The genetic code and the codes of tradition were recognized for a very long time and signify the ancient origin of this ebook. what's fairly new during this box is the learn of all codes that got here after the genetic code and prior to the codes of tradition.

The Routledge Handbook of Language and Identity

The Routledge guide of Language and identification offers a transparent and entire survey of the sector of language and id from an utilized linguistics point of view. 41 chapters are organised into 5 sections overlaying: theoretical views informing language and id stories key matters for researchers doing language and id reports different types and dimensions of id identification in language studying contexts and between language newbies destiny instructions for language and identification reports in utilized linguistics Written through experts from around the globe, every one bankruptcy will introduce an issue in language and id reports, offer a concise and important survey, during which the significance and relevance to utilized linguists is defined and comprise extra examining.

Extra info for Ambiguity Resolution in Language Learning: Computational and Cognitive Models

Sample text

Transformation-based tagging as introduced by Brill (1993a),(1993b) also requires a hand-tagged text for training. The model in transformation-based tagging consists of a set of templates for tagging rules such as the ones in (24). (24) a. change tag X to tag Y after tag Z b. change tag X to tag Y after word W Initially, each word is tagged with its most probable tag. , those compatible with the pre-selected rule schemata), tests their effect on the corpus, and chooses the one that improves overall tagging accuracy most.

Consider two infrequent adjectives that happen to modify different nouns in the corpus. Their right similarity according to the cosine measure would be zero. This is clearly undesirable. But even with highfrequency words, the simple vector model can yield misleading similarity measurements. A case in point is "a" vs. "an". These two articles do not share any right neighbors since the former is only used before consonants and the latter only before vowels. Yet intuitively, they are similar with respect to their right syntactic context despite the lack of common right neighbors.

This is clearly undesirable. But even with highfrequency words, the simple vector model can yield misleading similarity measurements. A case in point is "a" vs. "an". These two articles do not share any right neighbors since the former is only used before consonants and the latter only before vowels. Yet intuitively, they are similar with respect to their right syntactic context despite the lack of common right neighbors. One solution to these problems is the application of a singular value decomposition (SVD) (Golub and van Loan, 1989).

Download PDF sample

Rated 4.60 of 5 – based on 16 votes