We investigate the effect of encoding additional semantic and syntactic information sources in a classification-based machine learning approach to the task of coreference resolutio...
Recently, significant progress has been made on learning structured predictors via coordinated training algorithms such as conditional random fields and maximum margin Markov ne...
PropBank has been widely used as training data for Semantic Role Labeling. However, because this training data is taken from the WSJ, the resulting machine learning models tend to...
Feature selection, as a preprocessing step to machine learning, has been very effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and imp...
Mining bilingual data (including bilingual sentences and terms1 ) from the Web can benefit many NLP applications, such as machine translation and cross language information retrie...
Long Jiang, Shiquan Yang, Ming Zhou, Xiaohua Liu, ...