Skip to main content

List of Theses

For advanced search options you can also view this in the Forschungsinformationssystem of the TU Dresden.

Transition-based Generation from Abstract Meaning Representations
Art der Abschlussarbeit
Master
Autoren
  • Schick, Timo
Betreuer
  • Prof. Dr.-Ing. habil. Heiko Vogler
Abstract
This work addresses the task of generating English sentences from Abstract Meaning Representation (AMR) graphs. To cope with this task, we transform each input AMR graph into a structure similar to a dependency tree and annotate it with syntactic information by applying various predefined actions to it. Subsequently, a sentence is obtained from this tree structure by visiting its nodes in a specific order. We train maximum entropy models to estimate the probability of each individual action and devise an algorithm that efficiently approximates the best sequence of actions to be applied. Our generator achieves a Bleu score of 27.4 on the LDC2014T12 test set.
Schlagwörter
abstract meaning reprsentation, transition, generation
Berichtsjahr
2017
Last modified: 2020-10-26 10:29am