# Meaning Representation of Numeric Fused-Heads in UCCA

arXiv: https://arxiv.org/abs/2106.07364 · HTML: https://mlsanity.com/paper/2106.07364/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution](https://mlsanity.com/paper/1905.10886/) (2019)
- [Prague Dependency Treebank -- Consolidated 1.0](https://mlsanity.com/paper/2006.03679/) (2020)
- [Content Differences in Syntactic and Semantic Representations](https://mlsanity.com/paper/1903.06494/) (2019)
- [Refining Implicit Argument Annotation for UCCA](https://mlsanity.com/paper/2005.12889/) (2020)
- [UCCA's Foundational Layer: Annotation Guidelines v2.1](https://mlsanity.com/paper/2012.15810/) (2020)

## Abstract (arXiv)

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.