Punctuation Processing for Projective Dependency Parsing

Modern statistical dependency parsers assign lexical heads to punctuations as well as words. Punctuation parsing errors lead to low parsing accuracy on words. In this work, we propose an alternative approach to addressing punctuation in dependency parsing. Rather than assigning lexical heads to punctuations, we treat punctuations as properties of their neighbouring words, used as features to guide the parser to build the dependency graph. Integrating our method with an arc-standard parser yields a 93.06% unlabelled attachment score, which is the best accuracy by a single-model transition-based parser reported so far.