Auxiliary Tasks to Boost Biaffine Semantic Dependency Parsing - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Auxiliary Tasks to Boost Biaffine Semantic Dependency Parsing

Marie Candito

Abstract

The biaffine parser of Dozat and Manning (2017) was successfully extended to semantic dependency parsing (SDP) (Dozat and 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 (modulo a shared representation of tokens). To circumvent such an independence of decision, while retaining the O(n 2) 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 state-ofthe-art baseline using transformer-based contextualized representations. This provides a simple and robust method to boost SDP performance.
Fichier principal
Vignette du fichier
aux_task_biaffine_graph_parsing_FindingsACL22.pdf (259.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03676655 , version 1 (24-05-2022)

Identifiers

  • HAL Id : hal-03676655 , version 1

Cite

Marie Candito. Auxiliary Tasks to Boost Biaffine Semantic Dependency Parsing. Findings of the Association for Computational Linguistics: ACL 2022, May 2022, Dublin, Ireland. ⟨hal-03676655⟩
57 View
44 Download

Share

Gmail Facebook X LinkedIn More