Skip to Main content Skip to Navigation
Conference papers

A Hierarchical Model for Data-to-Text Generation

Abstract : 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.
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-02774325
Contributor : Laure Soulier <>
Submitted on : Thursday, June 4, 2020 - 1:57:28 PM
Last modification on : Tuesday, June 30, 2020 - 2:28:10 PM

Links full text

Identifiers

Citation

Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten, Patrick Gallinari. A Hierarchical Model for Data-to-Text Generation. 42nd European Conference on IR Research, ECIR 2020, Apr 2020, Lisbon, Portugal. pp.65-80, ⟨10.1007/978-3-030-45439-5_5⟩. ⟨hal-02774325⟩

Share

Metrics

Record views

51