paper-with-me

Concept-To-Text Generation

1개 벤치마크 · 논문 17편 · 이 태스크의 논문 보기 →

Benchmarks

COCO Captions

결과 1개

Most implemented

Papers

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

2022-10-07 · Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu 외

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 Generation

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

2021-09-08 · AKBC Workshop CSKB 2021 10 · Steven Y. Feng, Kevin Lu, Zhuofu Tao, Malihe Alikhani 외

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 Grounding

SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation

2021-08-15 · INLG (ACL) 2021 8 · Steven Y. Feng, Jessica Huynh, Chaitanya Narisetty, Eduard Hovy 외

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 Generation

TUDA-Reproducibility @ ReproGen: Replicability of Human Evaluation of Text-to-Text and Concept-to-Text Generation

2021-08-01 · INLG (ACL) 2021 8 · Christian Richter, Yanran Chen, Steffen Eger

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 Generation

Informed Sampling for Diversity in Concept-to-Text NLG

2020-04-29 · Findings (EMNLP) 2021 11 · Giulio Zhou, Gerasimos Lampouras

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 Generation

Enhancing Topic-to-Essay Generation with External Commonsense Knowledge

2019-07-01 · ACL 2019 7 · Pengcheng Yang, Lei LI, Fuli Luo, Tianyu Liu 외

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

전체 17편 보기 →