Abstract

In this paper, we propose a novel solution to the problem of assigning function labels to syntactic constituents. This task is a useful intermediate step between syntactic parsing and semantic role labelling. What distinguishes our proposal from other attempts in function or semantic role labelling is that we perform the learning of function labels at the same time as parsing. We reach state-of-the-art performance both on parsing and function labelling. Our results indicate that function label information is located in the lower levels of the parse tree, and that, similarly to other function and semantic labelling results, the main difficulty lies in distinguishing constituents that bear a function label from constituents that do not. 1

Citations