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.
ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models
Comparing Computational Architectures for Automated Journalism
Vision Transformer Based Model for Describing a Set of Images as a Story
Calibrating Sequence likelihood Improves Conditional Language Generation
XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages
Selective Token Generation for Few-shot Natural Language Generation
Coherent Visual Storytelling via Parallel Top-Down Visual and Topic Attention
High Recall Data-to-text Generation with Progressive Edit
Innovations in Neural Data-to-text Generation: A Survey
Leveraging Natural Supervision for Language Representation Learning and Generation
Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model
Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency
SentiStory: A Multi-Layered Sentiment-Aware Generative Model for Visual Storytelling
Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation
CoNT: Contrastive Neural Text Generation
R2D2: Robust Data-to-Text with Replacement Detection
What Makes Data-to-Text Generation Hard for Pretrained Language Models?
RoViST:Learning Robust Metrics for Visual Storytelling
Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning
NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures
GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation
Neural Pipeline for Zero-Shot Data-to-Text Generation
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods
Knowledge-enriched Attention Network with Group-wise Semantic for Visual Storytelling
Data-to-text Generation with Variational Sequential Planning
Survey of Hallucination in Natural Language Generation
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages
A System for Image Understanding using Sensemaking and Narrative
Discourse Analysis for Evaluating Coherence in Video Paragraph Captions
Visual Storytelling with Hierarchical BERT Semantic Guidance
A Survey of Natural Language Generation
May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generation
Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
Search and Learn: Improving Semantic Coverage for Data-to-Text Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.