Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

@article{Naseem2019RewardingST,
  title={Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning},
  author={Tahira Naseem and Abhishek K. Shah and Hui Wan and Radu Florian and Salim Roukos and Miguel Ballesteros},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.13370}
}
Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published… CONTINUE READING

Similar Papers

Tables and Topics from this paper.

Citations

Publications citing this paper.

AMR Parsing as Sequence-to-Graph Transduction

VIEW 2 EXCERPTS
CITES RESULTS & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

AMR Parsing using Stack-LSTMs

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Self-Critical Sequence Training for Image Captioning

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL