Auxiliary tasks to boost Biaffine Semantic Dependency Parsing

Abstract

The biaffine syntactic parser of Dozat & Manning (2017) was successfully extended to semantic dependency graph parsing (SDP) (Dozat & Manning, 2018). Its performance on graphs is surprisingly high given that, without the constraint of producing a tree, all arcs for a given sentence are predicted independently from each other. To address this issue, while retaining the O(n2) complexity and highly parallelizable architecture, we propose to use simple auxiliary tasks that introduce some form of interdependence between arcs. Experiments on the three English acyclic datasets of SemEval-2015 task 18 (Oepen et al., 2015), and on French deep syntactic cyclic graphs (Ribeyre et al., 2014) show modest but systematic performance gains on a near-SOTA baseline using transformer-based contextualized representations. This provides a simple and robust method to boost SDP performance.