Ensembling Graph Predictions for AMR Parsing
This work addresses the problem of improving accuracy in graph-based predictions, such as AMR parsing, for natural language processing researchers and practitioners, though it is incremental as it extends ensembling techniques to a new domain.
The paper tackles the problem of ensembling graph predictions, which is understudied compared to classification or regression, by formalizing it as mining the largest supported graph and proposing an efficient heuristic algorithm. Experimental results show that the approach combines state-of-the-art AMR parsers to create predictions more accurate than any individual model on five standard benchmark datasets.
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.