Punctuation Processing for Projective Dependency Parsing
Ji Ma, Yue Zhang, Jingbo Zhu · 2014
Modern statistical dependency parsers as-sign 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 punctu-ations as properties of their neighbour-ing words, used as features to guide the parser to build the dependency graph. In-tegrating our method with an arc-standard parser yields a 93.06 % unlabelled attach-ment score, which is the best accuracy by a single-model transition-based parser re-ported so far. 1