Can I read Normalizing Compositional Structures Across Graphbanks on EtoBox?

Normalizing Compositional Structures Across Graphbanks by Donatelli, Lucia; Groschwitz, Jonas; Koller, Alexander; Lindemann, Matthias; Weißenhorn, Pia is a scholarly article available to read on EtoBox.

What is Normalizing Compositional Structures Across Graphbanks about?

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.

Author

Donatelli, Lucia; Groschwitz, Jonas; Koller, Alexander; Lindemann, Matthias; Weißenhorn, Pia

Published

2020

Language

EN