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.
Open Domain Question Answering with A Unified Knowledge Interface
Improving Compositional Generalization with Self-Training for Data-to-Text Generation
Control Prefixes for Parameter-Efficient Text Generation
Perturbation CheckLists for Evaluating NLG Evaluation Metrics
Biomedical Data-to-Text Generation via Fine-Tuning Transformers
Plan-then-Generate: Controlled Data-to-Text Generation via Planning
Ordered Attention for Coherent Visual Storytelling
WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
HTLM: Hyper-Text Pre-Training and Prompting of Language Models
On Training Instance Selection for Few-Shot Neural Text Generation
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
Stage-wise Fine-tuning for Graph-to-Text Generation
Plot and Rework: Modeling Storylines for Visual Storytelling
R2D2: Relational Text Decoding with Transformers
Learning to Reason for Text Generation from Scientific Tables
Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation
On Hallucination and Predictive Uncertainty in Conditional Language Generation
Structural Adapters in Pretrained Language Models for AMR-to-text Generation
Structural Information Preserving for Graph-to-Text Generation
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning
Neural Data-to-Text Generation with LM-based Text Augmentation
Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling
Data-to-text Generation with Macro Planning
Controlling Hallucinations at Word Level in Data-to-Text Generation
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Data-to-text Generation by Splicing Together Nearest Neighbors
Transforming Multi-Conditioned Generation from Meaning Representation
How to Train Your Agent to Read and Write
WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling
Latent Template Induction with Gumbel-CRFs
Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference
DORB: Dynamically Optimizing Multiple Rewards with Bandits
Data-to-Text Generation with Iterative Text Editing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.