We present an approach to constituent parsing, which is driven by classifiers induced to minimize a single regularized objective. It is the first discriminatively-trained constituent parser to surpass the Collins (2003) parser without using a generative model. Our primary contribution is simplifying the human effort required for feature engineering. Our model can incorporate arbitrary features ...

According to the dual-route race model of compound word identification (Pollatsek, Hyönä, & Bertram, 2000), the holistic route and the morphological decomposition route operate in tandem. Bertram and Hyönä (2003) posited that word length modulates the interplay between the two access routes. When a compound word is sufficiently short so that all or most of its letters fall on the foveal region ...