English

Parser for Abstract Meaning Representation using Learning to Search

Computation and Language 2015-10-27 v1

Abstract

We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, a Learning to Search approach, by modeling the concept and the relation learning in a unified framework. We evaluate our parser on multiple datasets from varied domains and show an absolute improvement of 2% to 6% over the state-of-the-art. Additionally we show that using the most frequent concept gives us a baseline that is stronger than the state-of-the-art for concept prediction. We plan to release our parser for public use.

Keywords

Cite

@article{arxiv.1510.07586,
  title  = {Parser for Abstract Meaning Representation using Learning to Search},
  author = {Sudha Rao and Yogarshi Vyas and Hal Daume and Philip Resnik},
  journal= {arXiv preprint arXiv:1510.07586},
  year   = {2015}
}
R2 v1 2026-06-22T11:29:12.820Z