TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/A Hierarchical Model for Data-to-Text Generation

A Hierarchical Model for Data-to-Text Generation

Clément Rebuffel, Laure Soulier, Geoffrey Scoutheeten, Patrick Gallinari

2019-12-20Data-to-Text GenerationText GenerationTranslation
PaperPDFCode(official)

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.

Results

TaskDatasetMetricValueModel
Text GenerationRotoWire (Relation Generation)count21.17Hierarchical Transformer Encoder + conditional copy
Text GenerationRotoWire (Content Ordering)BLEU17.5Hierarchical Transformer Encoder + conditional copy
Text GenerationRotoWireBLEU17.5Hierarchical transformer encoder + conditional copy
Data-to-Text GenerationRotoWire (Relation Generation)count21.17Hierarchical Transformer Encoder + conditional copy
Data-to-Text GenerationRotoWire (Content Ordering)BLEU17.5Hierarchical Transformer Encoder + conditional copy
Data-to-Text GenerationRotoWireBLEU17.5Hierarchical transformer encoder + conditional copy

Related Papers

Making Language Model a Hierarchical Classifier and Generator2025-07-17A Translation of Probabilistic Event Calculus into Markov Decision Processes2025-07-17Mitigating Object Hallucinations via Sentence-Level Early Intervention2025-07-16The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs2025-07-15Seq vs Seq: An Open Suite of Paired Encoders and Decoders2025-07-15Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking2025-07-15Function-to-Style Guidance of LLMs for Code Translation2025-07-15Exploiting Leaderboards for Large-Scale Distribution of Malicious Models2025-07-11