Capturing Entity Hierarchy in Data-to-Text Generative Models - Sorbonne Université
Conference Papers Year : 2020

Capturing Entity Hierarchy in Data-to-Text Generative Models

Abstract

We aim at generating summary from structured data (i.e. tables, entity-relation triplets, ...). Most previous approaches relies on an encoder-decoder architecture in which data are linearized into a sequence of elements. In contrast, we propose to take into account entities forming the data structure in a hierarchical model. More-over, we introduce the Transformer encoder in data-to-text models to ensure robust encoding of each element/entities in comparison to all others, no matter their initial positioning. Our model is evaluated on the RotoWire benchmark (statistical tables of NBA basketball games). This paper has been accepted at ECIR 2020.
No file

Dates and versions

hal-03479813 , version 1 (14-12-2021)

Identifiers

  • HAL Id : hal-03479813 , version 1

Cite

Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten, Patrick Gallinari. Capturing Entity Hierarchy in Data-to-Text Generative Models. First Joint Conference of the Information Retrieval Communities in Europe (CIRCLE 2020), Jul 2020, Online, France. ⟨hal-03479813⟩
48 View
0 Download

Share

More