Recent work has shown that very large corpora can act as training data for NLP algorithms even without explicit labels. In this paper we show how the use of surface features and paraphrases in queries against search engines can be used to infer labels for structural ambiguity resolution tasks. Using unsupervised algorithms, we achieve 84% precision on PP-attachment and 80% on noun compound coor...

In this paper, we outline a theory of referential accessibility called Veins Theory (VT). We show how VT addresses the problem of "left satellites", currently a problem for stack-based models, and show that VT can be used to significantly reduce the search space for antecedents. We also show that VT provides a better model for determining domains of referential accessibility, and discuss how VT...

The ?-MEU model and the smooth ambiguity are two popular models in decision making under ambiguity. However, axiomatic foundations of these not completely understood. We provide a symmetric setting with product state space S?. This allows marginals over S to be linked behaviorally (limiting frequency) events. Bets on such events shown reveal i.i.d. measures that relevant for maker's preferences...

In this paper a new approach to handwritten mathematical expression recognition is presented. The approach is highly original in that the solution, an expression tree, is immediately updated whenever the user writes a new stroke. Fuzzy logic is used extensively, in both the symbol recognition and structural analysis phases, which is appropriate given the amount of imprecision and ambiguity pres...

In natural language processing, ambiguity resolution is a central issue, and can be regarded as a preference assignment problem. In this paper, a Generalized Probabilistic Semantic Model (GPSM) is proposed for preference computation. An effective semantic tagging procedure is proposed for tagging semantic features. A semantic score function is derived based on a score function, which integrates...

In this paper an information theoretic approach is provided for resolving border ambiguity under partial occlusion. The proposed framework allows structural interpretation of images prior to the application of domain specific knowledge. The central idea behind MDL based figure-ground grouping is merging those place-token candidates whose composed description length (whole) is better than sum of...

This paper evaluates whether or not simplicity or "minimalistic" heuristics, which are posited to account for local ambiguity resolution at the level of structural processing and for the lack of inferential elaboration during discourse processing, represent the most accurate account of language processing. Evidence from on-line studies is presented which suggests that alternative, more knowledg...