Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation
2017-09-01WS 2017Unverified0· sign in to hype
Thiago Castro Ferreira, Iacer Calixto, S Wubben, er, Emiel Krahmer
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
In this paper, we study AMR-to-text generation, framing it as a translation task and comparing two different MT approaches (Phrase-based and Neural MT). We systematically study the effects of 3 AMR preprocessing steps (Delexicalisation, Compression, and Linearisation) applied before the MT phase. Our results show that preprocessing indeed helps, although the benefits differ for the two MT models.