this paper is an attempt to explore the prepositions used to encode the agent in persian passive constructions. according to givón (1983) the main function of the passive constructions is to defocus the agent. as the general trend in persian is to omit this defocused agent, we will stylistically divide the passive constructions into two main sub branches, namely unmarked and marked passives acc...

This paper proposes a machine-learning based approach to predict accurately, given a syntactic and semantic context, which preposition is most likely to occur in that context. Each occurrence of a preposition in an English corpus has its context represented by a vector containing 307 features. The vectors are processed by a voted perceptron algorithm to learn associations between contexts and p...

Representation and Prediction Features Initial experiments showed that replacing prepositions by simple place-holders decreases the translation quality. As an extension to the basic approach with plain place-holders, we thus experiment with enriching the place-holders such that they contain more relevant information and represent the content of a preposition while still being in an abstract for...

We show that existing methods for training preposition error correction systems, whether using well-edited text or error-annotated corpora, do not generalize across very different test sets. We present a new, large errorannotated corpus and use it to train systems that generalize across three different test sets, each from a different domain and with different error characteristics. This new co...