Paper: Forest Reranking through Subtree Ranking

ACL ID D12-1095
Title Forest Reranking through Subtree Ranking
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2012

We propose the subtree ranking approach to parse forest reranking which is a general- ization of current perceptron-based reranking methods. For the training of the reranker, we extract competing local subtrees, hence the training instances (candidate subtree sets) are very similar to those used during beam- search parsing. This leads to better param- eter optimization. Another chief advantage of the framework is that arbitrary learning to rank methods can be applied. We evaluated our reranking approach on German and En- glish phrase structure parsing tasks and com- pared it to various state-of-the-art reranking approaches such as the perceptron-based for- est reranker. The subtree ranking approach with a Maximum Entropy model significantly outperformed the other approaches.