2019/12/20 by Clément Rebuffel, Rebuffel, Clément, Laure Soulier +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #cs.CL #cs.IR #cs.LG
paper · pdf · doi:10.48550/arxiv.1912.10011
Accepted at the 42nd European Conference on IR Research, ECIR 2020
arxiv created 2019/12/20 · arxiv updated 2019/12/23
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.