The Interplay Between Loss Functions and Structural Constraints in Dependency Parsing
Robin Kurtz and Marco Kuhlmann. The Interplay Between Loss Functions and Structural Constraints in Dependency Parsing. Northern European Journal of Language Technology, 6:43–66, 2019.
Dependency parsing can be cast as a combinatorial optimization problem with the objective to find the highest-scoring graph, where edge scores are learnt from data. Several of the decoding algorithms that have been applied to this task employ structural restrictions on candidate solutions, such as the restriction to projective dependency trees in syntactic parsing, or the restriction to noncrossing graphs in semantic parsing. In this paper we study the interplay between structural restrictions and a common loss function in neural dependency parsing, the structural hingeloss. We show how structural constraints can make networks trained under this loss function diverge and propose a modified loss function that solves this problem. Our experimental evaluation shows that the modified loss function can yield improved parsing accuracy, compared to the unmodified baseline.