Meaning Representation of Numeric Fused-Heads in UCCA

TL;DR

This paper investigates the inconsistent handling of numeric fused-heads (NFHs) in UCCA parsing, highlighting its importance for accurate meaning representation and downstream NLP tasks involving numeric reasoning.

Contribution

It identifies the limitations of current UCCA parsers regarding NFHs and emphasizes the need for better annotation and modeling of this phenomenon.

Findings

NFHs are inconsistently addressed in current UCCA parsers.

Proper annotation of NFHs can improve downstream NLP tasks.

The paper encourages further research on NFHs in meaning representations.

Abstract

We exhibit that the implicit UCCA parser does not address numeric fused-heads (NFHs) consistently, which could result either from inconsistent annotation, insufficient training data or a modelling limitation. and show which factors are involved. We consider this phenomenon important, as it is pervasive in text and critical for correct inference. Careful design and fine-grained annotation of NFHs in meaning representation frameworks would benefit downstream tasks such as machine translation, natural language inference and question answering, particularly when they require numeric reasoning, as recovering and categorizing them. We are investigating the treatment of this phenomenon by other meaning representations, such as AMR. We encourage researchers in meaning representations, and computational linguistics in general, to address this phenomenon in future research.