Learning context-dependent choice functions

Deep architectures for learning context-dependent ranking functions

Object ranking is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects, which are typically represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. Current approaches commonly focus on ranking by scoring, i.e., on learning an underlying latent ut...

Learning Context Dependent Concepts

This article presents the concept of context dependent classiication. In context dependent classiication of elementary objects, an elementary object is represented by a node in a graph. A node can be identiied to belong to a certain node class, if one of the characterizing contexts for that class can be embedded in the graph properly. Thus, the classiication of a node does not only depend on pr...

Dependent plural pronouns with Skolemized choice functions

The present paper discusses two interesting phenomena concerning phifeatures on plural pronouns: (i) plural pronouns that denote atomic individuals (‘dependent plural pronouns’), and (ii) plural pronouns with more than one binder (‘partial binding’). A novel account of these two phenomena is proposed, according towhich all occurrences of phi-features are both semantically and morphologically re...

A Route Choice Model with Context-Dependent Value of Time

Context-dependent regulation of hematopoietic lineage choice by HEBAlt.

Hematopoietic development is controlled by combinatorial interactions between E-protein transcription factors and other lineage regulators that operate in the context of gene-regulatory networks. The E-proteins HEB and E2A are critical for T cell and B cell development, but the mechanisms by which their activities are directed to different genes in each lineage are unclear. We found that a shor...