Neural attention models have achieved great success in different NLP tasks. How- ever, they have not fulfilled their promise on the AMR parsing task due to the data sparsity issue. In this paper, we de- scribe a sequence-to-sequence model for AMR parsing and present different ways to tackle the data sparsity problem. We show that our methods achieve significant improvement over a baseline neural atten- tion model and our results are also compet- itive against state-of-the-art systems that do not use extra linguistic resources.
@article{arxiv.1702.05053,
title = {Addressing the Data Sparsity Issue in Neural AMR Parsing},
author = {Xiaochang Peng and Chuan Wang and Daniel Gildea and Nianwen Xue},
journal= {arXiv preprint arXiv:1702.05053},
year = {2017}
}