# AMR Quality Rating with a Lightweight CNN

arXiv: https://arxiv.org/abs/2005.12187 · HTML: https://mlsanity.com/paper/2005.12187/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 4 of 4)

- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [Weisfeiler-Leman in the BAMBOO: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similarity](https://mlsanity.com/paper/2108.11949/) (2021)
- [Better Smatch = Better Parser? AMR evaluation is not so simple anymore](https://mlsanity.com/paper/2210.06461/) (2022)
- [SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance](https://mlsanity.com/paper/2203.13226/) (2022)

## Abstract (arXiv)

Structured semantic sentence representations such as Abstract Meaning Representations (AMRs) are potentially useful in various NLP tasks. However, the quality of automatic parses can vary greatly and jeopardizes their usefulness. This can be mitigated by models that can accurately rate AMR quality in the absence of costly gold data, allowing us to inform downstream systems about an incorporated parse's trustworthiness or select among different candidate parses. In this work, we propose to transfer the AMR graph to the domain of images. This allows us to create a simple convolutional neural network (CNN) that imitates a human judge tasked with rating graph quality. Our experiments show that the method can rate quality more accurately than strong baselines, in several quality dimensions. Moreover, the method proves to be efficient and reduces the incurred energy consumption.