We present a transition-based parser that jointly produces syntactic andsemantic dependencies. It learns a representation of the entire algorithmstate, using stack long short-term memories. Our greedy inference
20 Nov 2019·Zuchao Li,Hai Zhao,Kevin Parnow· Most syntactic dependency parsing models may fall into one of two categories: transition- and graph-based models. The former models enjoy high inference efficiency with linear time complexity, but they rely on the stacking or re-ranking of partial...