Search Results - "Rebuffel, Clément"

Controlling hallucinations at word level in data-to-text generation by Rebuffel, Clement, Roberti, Marco, Soulier, Laure, Scoutheeten, Geoffrey, Cancelliere, Rossella, Gallinari, Patrick

“…Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field…”
Get full text

PARENTing via Model-Agnostic Reinforcement Learning to Correct Pathological Behaviors in Data-to-Text Generation by Rebuffel, Clément, Soulier, Laure, Scoutheeten, Geoffrey, Gallinari, Patrick

“…In language generation models conditioned by structured data, the classical training via maximum likelihood almost always leads models to pick up on dataset…”
Get full text

A Hierarchical Model for Data-to-Text Generation by Rebuffel, Clément, Soulier, Laure, Scoutheeten, Geoffrey, Gallinari, Patrick

“…Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally…”
Get full text

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation by Rebuffel, Clément, Scialom, Thomas, Soulier, Laure, Piwowarski, Benjamin, Lamprier, Sylvain, Staiano, Jacopo, Scoutheeten, Geoffrey, Gallinari, Patrick

“…QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and…”
Get full text

Controlling Hallucinations at Word Level in Data-to-Text Generation by Rebuffel, Clément, Roberti, Marco, Soulier, Laure, Scoutheeten, Geoffrey, Cancelliere, Rossella, Gallinari, Patrick

“…Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field…”
Get full text