# Robust Subgraph Generation Improves Abstract Meaning Representation Parsing

Source: [Robust Subgraph Generation Improves Abstract Meaning Representation Parsing](<https://www.sota2.com/research/paper/68fa61e61e209131ce9f68c6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:08:28.563Z

Authors: Keenon Werling, Gabor Angeli, Christopher Manning

Published: 2015-06-10T00:40:12.000Z

## Abstract

The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dictionary lookup, is currently an important limiting factor in AMR parsing. We propose a small set of actions that derive AMR subgraphs by transformations on spans of text, which allows for more robust learning of this stage. Our set of construction actions generalize better than the previous approach, and can be learned with a simple classifier. We improve on the previous state-of-the-art result for AMR parsing, boosting end-to-end performance by 3 F$\_1$ on both the LDC2013E117 and LDC2014T12 datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [AMR parsing on LDC2014T12 Newswire section](<https://www.sota2.com/research/sota/amr-parsing-on-ldc2014t12-newswire-section.md>): AMR parsing; LDC2014T12 Newswire section; F1 Score: 62.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1506.03139>)

[PDF](<https://arxiv.org/pdf/1506.03139.pdf>)