A Hierarchical Model for Data-to-Text Generation
This work addresses the challenge of generating natural language from structured data for applications like automated reporting, but it appears incremental as it builds on existing encoder-decoder methods.
The paper tackles the problem of data-to-text generation by addressing the loss of structure when linearizing data, proposing a hierarchical model that encodes at element and structure levels, and shows effectiveness on the RotoWire dataset with qualitative and quantitative improvements.
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.