Download Ambiguity Resolution in Language Learning: Computational and by Hinrich Schütze PDF

By Hinrich Schütze

This quantity is worried with how ambiguity and ambiguity answer are realized, that's, with the purchase of different representations of ambiguous linguistic types and the data important for choosing between them in context. Schütze concentrates on how the purchase of ambiguity is feasible in precept and demonstrates that individual forms of algorithms and studying architectures (such as unsupervised clustering and neural networks) can be triumphant on the activity. 3 varieties of lexical ambiguity are handled: ambiguity in syntactic categorisation, semantic categorisation, and verbal subcategorisation. the quantity offers 3 diversified versions of ambiguity acquisition: Tag house, notice area, and Subcat Learner, and addresses the significance of ambiguity in linguistic illustration and its relevance for linguistic innateness.

Show description

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

Best semantics books

Economy and Semantic Interpretation

In financial system and Semantic Interpretation, Danny Fox investigates the relevance of ideas of optimization (economy) to the interface among syntax and semantics. assisting the view that grammar is specific by means of financial system concerns, Fox argues for varied financial system stipulations that constrain the program of "covert" operations.

The Geometry of Meaning: Semantics Based on Conceptual Spaces

Within the Geometry of that means, Peter Gärdenfors proposes a idea of semantics that bridges cognitive technological know-how and linguistics and indicates how theories of cognitive procedures, particularly inspiration formation, might be exploited in a basic semantic version. He argues that our minds arrange the knowledge excited by communicative acts in a structure that may be modeled in geometric or topological phrases -- in what he phrases conceptual areas, extending the idea he provided in an previous publication by means of that identify.

Mother Zion in Deutero-Isaiah: A Metaphor for Zion Theology

Mom Zion in Deutero-Isaiah: A Metaphor for Zion Theology bargains the original standpoint that personified mom Zion in Deutero-Isaiah is not only a metaphor used for a rhetorical objective yet a cognitive metaphor representing Zion theology, a relevant topic within the publication of Isaiah. the writer deftly combines the tools of metaphor conception and intertextuality to give an explanation for the important yet frequently ignored conundrum that Zion in Deutero-Isaiah is an blameless mom, not like the adulterous spouse in different prophetic books.

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

Sample text

Why should it be our goal to reproduce one of the many possibilities that was chosen by the collectors of the SYNTACTIC CATEGORIZATION / 41 Brown corpus? To put it differently, other human-made tag sets would also fare badly if they were evaluated for their ability to reproduce the Brown tag set. So an automatically generated tag set is not necessarily bad just because it does not reproduce the Brown tag set. For the reasons outlined above, the following evaluation procedure was chosen here: • Cluster tokens into 200 clusters.

1 million tokens and 47,025 word types. SYNTACTIC CATEGORIZATION / 35 The motivation for using the SVD is to address three problems, two of which were just discussed: • sparseness • generalization • compactness It is obvious how the last point is achieved: by reduction to a lowdimensional space the objects we need to deal with are smaller in size and we gain efficiency. SVD addresses the problems of sparseness and generalization because a high-dimensional space can represent more information than a low-dimensional space.

The rationale is that words with similar left context characterize words to their right in a similar way. For example, "seemed" and "would" SYNTACTIC CATEGORIZATION / 39 have similar left contexts, and they characterize the right contexts of "he" and "the firefighter" as potentially containing an inflected verb form. Rather than having separate entries in its right context vector for "seemed", "would", and "likes", a word like "he" can now be characterized by a generalized entry for "inflected verb form occurs frequently to my right".

Download PDF sample

Rated 4.81 of 5 – based on 20 votes