Concept-To-Text Generation
1개 벤치마크 · 논문 17편 · 이 태스크의 논문 보기 →
Benchmarks
COCO Captions
Most implemented
Neural Text Generation from Structured Data with Application to the Biography Domain
Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Papers
Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
Recent advances in text-to-image synthesis make it possible to visualize machine imaginations for a given context. On the other hand, when generating text, human writers are gifted at creative visualization, which enhanc…
Concept-To-Text GenerationImage GenerationStory GenerationText GenerationRetrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models
We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation. We perform experiments using BART and T5 on concept-to-…
Concept-To-Text GenerationSpecificityText GenerationVisual GroundingSAPPHIRE: Approaches for Enhanced Concept-to-Text Generation
We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on…
Concept-To-Text GenerationSpecificityText GenerationTUDA-Reproducibility @ ReproGen: Replicability of Human Evaluation of Text-to-Text and Concept-to-Text Generation
This paper describes our contribution to the Shared Task ReproGen by Belz et al. (2021), which investigates the reproducibility of human evaluations in the context of Natural Language Generation. We selected the paper “G…
Concept-To-Text GenerationPaper generationText GenerationInformed Sampling for Diversity in Concept-to-Text NLG
Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived flu…
Concept-To-Text GenerationDiversityImitation LearningText GenerationEnhancing Topic-to-Essay Generation with External Commonsense Knowledge
Automatic topic-to-essay generation is a challenging task since it requires generating novel, diverse, and topic-consistent paragraph-level text with a set of topics as input. Previous work tends to perform essay generat…
Concept-To-Text Generation