Papers with Code 아카이브
Data-to-Text Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 26
- 보존된 평가 기록
- 122
A classic problem in natural-language generation (NLG) involves taking structured data, such as a table, as input, and producing text that adequately and fluently describes this data as output. Unlike machine translation, which aims for complete transduction of the sentence to be translated, this form of NLG is usually taken to require addressing (at least) two separate challenges: what to say, the selection of an appropriate subset of the input data to discuss, and how to say it, the surface realization of a generation.
<span style="color:grey; opacity: 0.6">( Image credit: Data-to-Text Generation with Content Selection and Planning )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
Consistent Story Generation with Asymmetry Zigzag Sampling
Camera Trajectory Generation: A Comprehensive Survey of Methods, Metrics, and Future Directions
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers
Action2Dialogue: Generating Character-Centric Narratives from Scene-Level Prompts
StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation
VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?
FLIP Reasoning Challenge
Large Language Models as Span Annotators
GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography
Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling
DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description
VinaBench: Benchmark for Faithful and Consistent Visual Narratives
MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation
Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System
Toyteller: AI-powered Visual Storytelling Through Toy-Playing with Character Symbols
Curriculum Learning for Cross-Lingual Data-to-Text Generation With Noisy Data
An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation
Generative Visual Communication in the Era of Vision-Language Models
FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks
KAHANI: Culturally-Nuanced Visual Storytelling Pipeline for Non-Western Cultures
Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond
Generating Visual Stories with Grounded and Coreferent Characters
MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation
Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
Alfie: Democratising RGBA Image Generation With No $$$
Semantic Alignment for Multimodal Large Language Models
Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models
Context-aware Visual Storytelling with Visual Prefix Tuning and Contrastive Learning
Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation
ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context
Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.