A Hierarchical Model For Data-to-text Generation
Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten, Patrick Gallinari . Lecture Notes in Computer Science 2020 – 41 citations
[Paper]
Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as “data-to-text”. These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on translation encoder-decoder methods which linearize elements into a sequence. This however loses most of the structure contained in the data. In this work, we propose to overpass this limitation with a hierarchical model that encodes the data-structure at the element-level and the structure level. Evaluations on RotoWire show the effectiveness of our model w.r.t. qualitative and quantitative metrics.