By Hinrich Schütze
This quantity is worried with how ambiguity and ambiguity solution are realized, that's, with the purchase of the various representations of ambiguous linguistic types and the information invaluable for choosing between them in context. Schütze concentrates on how the purchase of ambiguity is feasible in precept and demonstrates that specific sorts of algorithms and studying architectures (such as unsupervised clustering and neural networks) can be triumphant on the job. 3 varieties of lexical ambiguity are handled: ambiguity in syntactic categorisation, semantic categorisation, and verbal subcategorisation. the quantity provides 3 varied versions of ambiguity acquisition: Tag area, observe house, and Subcat Learner, and addresses the significance of ambiguity in linguistic illustration and its relevance for linguistic innateness.
Read or Download Ambiguity Resolution in Language Learning: Computational and Cognitive Models PDF
Best semantics books
During this two-volume set Leonard Talmy defines the sector of cognitive semantics. He techniques the query of the way language organizes conceptual fabric either at a normal point and through reading a vital set of specific conceptual domain names: house and time, movement and site, causation and strength interplay, and a focus and point of view.
This ebook is exclusive in that it relates linguistic subfields: Semantics and Language Acquisition. the quantity features a choice of writings that specializes in semantic phenomena and their interpretation within the research of the language of a learner. the range of phenomena which are addressed is monstrous: temporal point and annoying, specificity, quantification, scope, finiteness, concentration constitution, and concentration debris.
Formal Pragmatics addresses concerns which are at the borderline of semantics and pragmatics of typical language, from the viewpoint of a model-theoretic semanticist. This up to date source covers a considerable physique of formal paintings on linguistic phenomena, and offers the way in which the semantics-pragmatics interface has emerge as seen this present day.
Cet ouvrage suggest une examine inédite du lexique chromatique : le mot de couleur y est analysé systématiquement dans une standpoint syntactico-sémantique ainsi que constructionnelle. Premièrement, l’étude se focalise sur l. a. position d’unités comme rouge au sein du lexique en les comparant aux noms de qualité auxquels ils sont à tort assimilés, puis aux autres termes chromatiques, noms (couleur, nuance …) et verbes (colorer, nuancer …).
- Inferential Role Semantics and the AnalyticSynthetic Distinction.
- The Meaning of Topic and Focus: The 59th Bridge Street Accent
- Modifying Adjuncts
- Semantics of Natural Language
- Pseudogapping and Ellipsis
Extra resources for Ambiguity Resolution in Language Learning: Computational and Cognitive Models
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.
Still, the methods can hardly settle issues of part-of-speech learnability since neither a part-of-speech lexicon nor an informant is available to children when they acquire language. g. the inside-outside algorithm (Charniak, 1993) or certain Bayesian methods (Stolcke, 1994; Chen, 1995). However, due to the difficulty of the problem of grammar induction, most experiments have either tried to learn from tagged text, thus assuming a solution to the tagging problem, (see the examples described in Charniak (1993) and Chen (1995)) or they have imposed artificial restrictions on the size of the vocabulary (less than 20 in Stolcke (1994)).
That is, each word-tag combination was replaced by a new word. For example, "to" occurs with the tags "TO" (infinitive marker) and "IN" (preposition). Each occurrence of "to" with tag "TO" was replaced by the new 40 / AMBIGUITY RESOLUTION IN LANGUAGE LEARNING word "to-TO" and each occurrence of "to" with tag "IN" was replaced by the new word "to-IN". A new disambiguated corpus was created by executing this procedure for all word-tag combinations. The induction procedure for natural contexts was then run on this disambiguated corpus.
Ambiguity Resolution in Language Learning: Computational and Cognitive Models by Hinrich Schütze