English

Normalizing Compositional Structures Across Graphbanks

Computation and Language 2020-05-01 v2

Abstract

The emergence of a variety of graph-based meaning representations (MRs) has sparked an important conversation about how to adequately represent semantic structure. These MRs exhibit structural differences that reflect different theoretical and design considerations, presenting challenges to uniform linguistic analysis and cross-framework semantic parsing. Here, we ask the question of which design differences between MRs are meaningful and semantically-rooted, and which are superficial. We present a methodology for normalizing discrepancies between MRs at the compositional level (Lindemann et al., 2019), finding that we can normalize the majority of divergent phenomena using linguistically-grounded rules. Our work significantly increases the match in compositional structure between MRs and improves multi-task learning (MTL) in a low-resource setting, demonstrating the usefulness of careful MR design analysis and comparison.

Keywords

Cite

@article{arxiv.2004.14236,
  title  = {Normalizing Compositional Structures Across Graphbanks},
  author = {Lucia Donatelli and Jonas Groschwitz and Alexander Koller and Matthias Lindemann and Pia Weißenhorn},
  journal= {arXiv preprint arXiv:2004.14236},
  year   = {2020}
}

Comments

16 pages, 6 figures