Generation from Abstract Meaning Representation using Tree Transducers
Abstract
Language generation from purely semantic representations is a challenging task. This paper addresses generating English from the Abstract Meaning Representation (AMR), consisting of re-entrant graphs whose nodes are concepts and edges are relations. The new method is trained statistically from AMR annotated English and consists of two major steps: (i) generating an appropriate spanning tree for the AMR, and (ii) applying tree-to-string transducers to generate English. The method relies on discriminative learning and an argument realization model to overcome data sparsity. Initial tests on held-out data show good promise despite the complexity of the task.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 12, 2016
- Accession Number
- AD1144586
Entities
People
- Chris Dyer
- Jaime Carbonell
- Jeffrey Flanigan
- Noah A. Smith
Organizations
- Carnegie Mellon University