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.
Can Knowledge Graphs Simplify Text?
Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Tackling Hallucinations in Neural Chart Summarization
Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs
Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation
Knowledge Graph for NLG in the context of conversational agents
You Can Generate It Again: Data-to-text Generation with Verification and Correction Prompting
Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
Faithful Low-Resource Data-to-Text Generation through Cycle Training
Pruning Pre-trained Language Models with Principled Importance and Self-regularization
ReTAG: Reasoning Aware Table to Analytic Text Generation
Iterative Adversarial Attack on Image-guided Story Ending Generation
Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain
Visual Transformation Telling
Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
A-CAP: Anticipation Captioning with Commonsense Knowledge
Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder
Detecting and Grounding Important Characters in Visual Stories
Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models
TabGenie: A Toolkit for Table-to-Text Generation
Multimodal Event Transformer for Image-guided Story Ending Generation
Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences
TextBox 2.0: A Text Generation Library with Pre-trained Language Models
Commentary Generation from Data Records of Multiplayer Strategy Esports Game
MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation
A survey on knowledge-enhanced multimodal learning
Time-aware Prompting for Text Generation
TaTa: A Multilingual Table-to-Text Dataset for African Languages
DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention
Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks
Mapping Process for the Task: Wikidata Statements to Text as Wikipedia Sentences
Table-To-Text generation and pre-training with TabT5
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.