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.
Template-free Data-to-Text Generation of Finnish Sports News
A Hierarchical Approach for Visual Storytelling Using Image Description
Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation
Character-Centric Storytelling
Induction and Reference of Entities in a Visual Story
What Makes A Good Story? Designing Composite Rewards for Visual Storytelling
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
Enhancing AMR-to-Text Generation with Dual Graph Representations
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
Learning to Select, Track, and Generate for Data-to-Text
Informative Visual Storytelling with Cross-modal Rules
"My Way of Telling a Story": Persona based Grounded Story Generation
Data-to-text Generation with Entity Modeling
Visual Story Post-Editing
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
Copy mechanism and tailored training for character-based data-to-text generation
An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing
A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method
Text Generation with Exemplar-based Adaptive Decoding
The Steep Road to Happily Ever After: An Analysis of Current Visual Storytelling Models
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
Text Generation from Knowledge Graphs with Graph Transformers
Pragmatically Informative Text Generation
Dixit: Interactive Visual Storytelling via Term Manipulation
Discourse Parsing in Videos: A Multi-modal Appraoch
On How Users Edit Computer-Generated Visual Stories
Hierarchical Photo-Scene Encoder for Album Storytelling
Data-to-Text Generation with Style Imitation
Deep Graph Convolutional Encoders for Structured Data to Text Generation
End-to-End Content and Plan Selection for Data-to-Text Generation
Findings of the E2E NLG Challenge
Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
Describing a Knowledge Base
Data-to-Text Generation with Content Selection and Planning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.