Using Syntax-Based Machine Translation to Parse English into Abstract Meaning Representation
Computation and Language
2015-04-29 v2 Artificial Intelligence
Abstract
We present a parser for Abstract Meaning Representation (AMR). We treat English-to-AMR conversion within the framework of string-to-tree, syntax-based machine translation (SBMT). To make this work, we transform the AMR structure into a form suitable for the mechanics of SBMT and useful for modeling. We introduce an AMR-specific language model and add data and features drawn from semantic resources. Our resulting AMR parser improves upon state-of-the-art results by 7 Smatch points.
Keywords
Cite
@article{arxiv.1504.06665,
title = {Using Syntax-Based Machine Translation to Parse English into Abstract Meaning Representation},
author = {Michael Pust and Ulf Hermjakob and Kevin Knight and Daniel Marcu and Jonathan May},
journal= {arXiv preprint arXiv:1504.06665},
year = {2015}
}
Comments
10 pages, 8 figures