Using Syntax-Based Machine Translation to Parse English into Abstract Meaning Representation
This work addresses the challenge of semantic parsing for natural language processing, offering a significant but incremental improvement in AMR parsing accuracy.
The authors tackled the problem of parsing English into Abstract Meaning Representation (AMR) by treating it as a string-to-tree, syntax-based machine translation task, resulting in a parser that improved state-of-the-art results by 7 Smatch points.
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.