Multilingual dependency parsing: A pipeline approach

This paper develops a general framework for machine learning based dependency parsing based on a pipeline approach, where a task is decomposed into several sequential stages. To overcome the error accumulation problem of pipeline models, we propose two natural principles for pipeline frameworks: (i) make local decisions as reli- able as possible, and (ii) reduce the number of sequential decisions made. We develop an algorithm that provably satises these princi- ples and show that the proposed principles support several algorith- mic choices that improve the dependency parsing accuracy signi- cantly. We present state of the art experimental results for English and several other languages.1