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.

Open PDF

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

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Aeronautical Laboratories
  • Algorithms
  • Artificial Intelligence
  • Computational Science
  • Computer Science
  • Demographic Cohorts
  • Hidden Markov Models
  • Language
  • Machine Translation
  • Machines
  • Markov Models
  • Military Research
  • Models
  • Natural Languages
  • Notation
  • Permutations
  • Probabilistic Models
  • Probability

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Distributed Systems and Data Platform Development