natural-language-processing-5

Concept-To-Text Generation

3260 papers • 126 benchmarks • 313 datasets

Generating natural language text from a conceptualized representation, such as an ontology.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in concept-to-text-generation-5

Trend

Dataset

Best Model

Actions

COCO Captions

Libraries

i

Use these libraries to find concept-to-text-generation-5 models and implementations

Datasets

COCO Captions

Subtasks

No subtasks available.

Most implemented papers

Neural Text Generation from Structured Data with Application to the Biography Domain

Michael Auli, David Grangier, R. Lebret•Wed Mar 23 2016

A neural model for concept-to-text generation that scales to large, rich domains and significantly out-performs a classical Kneser-Ney language model adapted to this task by nearly 15 BLEU is introduced.

564

Content

0

Paper Graph

SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation

E. Hovy, Varun Prashant Gangal, Steven Y. Feng, Jessica Huynh, Chaitanya Narisetty•Sat Aug 14 2021

An in-depth qualitative analysis illustrates that SAPPHIRE effectively addresses many issues of the baseline model generations, including lack of commonsense, insufficient specificity, and poor fluency.

11 0

Paper Graph

Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models

E. Hovy, T. Mitamura, Malihe Alikhani, Steven Y. Feng, Zhuofu Tao, Varun Gangal•Tue Sep 07 2021

Comprehensive evaluation and analysis demonstrate that VisCTG noticeably improves model performance while successfully addressing several issues of the baseline generations, including poor commonsense, fluency, and specificity.

14 0

Paper Graph

Adding a benchmark result helps the community track progress.