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.
Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition
Improving Visual Storytelling with Multimodal Large Language Models
CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation
Modeling Comparative Logical Relation with Contrastive Learning for Text Generation
SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation
Gorgeous: Create Your Desired Character Facial Makeup from Any Ideas
Bridging the Gap between Different Vocabularies for LLM Ensemble
Prompting for Numerical Sequences: A Case Study on Market Comment Generation
TARN-VIST: Topic Aware Reinforcement Network for Visual Storytelling
Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation
AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production
Metamorpheus: Interactive, Affective, and Creative Dream Narration Through Metaphorical Visual Storytelling
High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models
A Systematic Review of Data-to-Text NLG
SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling
TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
Self-training from Self-memory in Data-to-text Generation
Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation
Unifying Structured Data as Graph for Data-to-Text Pre-Training
MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising
DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models
Prompt Optimization via Adversarial In-Context Learning
Compositional Generalization for Data-to-Text Generation
PixT3: Pixel-based Table-To-Text Generation
inkn'hue: Enhancing Manga Colorization from Multiple Priors with Alignment Multi-Encoder VAE
TLM: Token-Level Masking for Transformers
ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation
GROOViST: A Metric for Grounding Objects in Visual Storytelling
Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation
Visual Storytelling with Question-Answer Plans
Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology
Comics for Everyone: Generating Accessible Text Descriptions for Comic Strips
A Survey on Interpretable Cross-modal Reasoning
TouchStone: Evaluating Vision-Language Models by Language Models
Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.