Ensembling Graph Predictions for AMR Parsing

TL;DR

This paper introduces a novel ensemble method for combining multiple graph predictions in AMR parsing, improving accuracy over individual models by formalizing the problem and proposing an efficient heuristic solution.

Contribution

It formalizes ensemble graph prediction as a maximum support graph problem and proposes a heuristic algorithm to approximate the NP-Hard solution, validated on AMR parsing tasks.

Findings

Ensemble predictions outperform individual models on five datasets.

The proposed heuristic effectively approximates the optimal ensemble.

Ensembling improves robustness and accuracy in AMR parsing.

Abstract

In many machine learning tasks, models are trained to predict structure data such as graphs. For example, in natural language processing, it is very common to parse texts into dependency trees or abstract meaning representation (AMR) graphs. On the other hand, ensemble methods combine predictions from multiple models to create a new one that is more robust and accurate than individual predictions. In the literature, there are many ensembling techniques proposed for classification or regression problems, however, ensemble graph prediction has not been studied thoroughly. In this work, we formalize this problem as mining the largest graph that is the most supported by a collection of graph predictions. As the problem is NP-Hard, we propose an efficient heuristic algorithm to approximate the optimal solution. To validate our approach, we carried out experiments in AMR parsing problems. The experimental results demonstrate that the proposed approach can combine the strength of state-of-the-art AMR parsers to create new predictions that are more accurate than any individual models in five standard benchmark datasets.