Y
Yoad Winter
Researcher at Utrecht University
Publications - 81
Citations - 2504
Yoad Winter is an academic researcher from Utrecht University. The author has contributed to research in topics: Reciprocal & Plural. The author has an hindex of 23, co-authored 78 publications receiving 2392 citations. Previous affiliations of Yoad Winter include Netherlands Institute for Advanced Study & Technion – Israel Institute of Technology.
Papers
More filters
Journal Article
Distributional word clusters vs. words for text categorization
TL;DR: An approach to text categorization that combines distributional clustering of words and a Support Vector Machine (SVM) classifier with a word-cluster representation is studied, which significantly outperforms the word-based representation in terms of categorization accuracy or representation efficiency.
Journal ArticleDOI
Choice functions and the scopal semantics of indefinites
TL;DR: In this paper, a revision des approches standard de la syntaxe and de la semantique des indefinis has been proposed, in which the quantification par les fonctions de choix est le mecanisme uniforme for l'interpretation of indefinis.
Journal ArticleDOI
Total adjectives vs. partial adjectives: Scale structure and higher-order modifiers
Carmen Rotstein,Yoad Winter +1 more
TL;DR: In this article, it is shown that the semantics of adjective phrases with modifiers such as almost, slightly, and completely are sensitive to whether the adjective is total or partial. And the effects of this theoretical distinction on the behavior of modified constructions are studied in detail and their ramifications for the semantic theory of adjectives are discussed.
Journal ArticleDOI
Vector Space Semantics: A Model-Theoretic Analysis of Locative Prepositions
Joost Zwarts,Yoad Winter +1 more
TL;DR: A compositional semantics of locativeprepositional phrases which is based on a vector space ontology, similar to the semanticuniversals of Generalized Quantifier Theory is introduced.
Proceedings ArticleDOI
On feature distributional clustering for text categorization
TL;DR: This work describes a text categorization approach that is based on a combination of feature distributional clusters with a support vector machine (SVM) classifier that yields high performance text classification that can outperform other recent methods in terms of categorization accuracy and representation efficiency.