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.
A Pipeline for Creative Visual Storytelling
Contextualize, Show and Tell: A Neural Visual Storyteller
Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling
GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation
Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
Bootstrapping Generators from Noisy Data
Oversampling for Imbalanced Learning Based on K-Means and SMOTE
Hierarchically-Attentive RNN for Album Summarization and Storytelling
The Code2Text Challenge: Text Generation in Source Code Libraries
Challenges in Data-to-Document Generation
The E2E Dataset: New Challenges For End-to-End Generation
Attention Is All You Need
Analysing Data-To-Text Generation Benchmarks
Content Selection in Data-to-Text Systems: A Survey
Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network
Visual Storytelling
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
Effective Approaches to Attention-based Neural Machine Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.