Papers with Code 아카이브
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/aistairc/market-reporter
공식 코드Prompting for Numerical Sequences: A Case Study on Market Comment Generation
https://github.com/aistairc/rotowire-modified
공식 코드https://github.com/aistairc/sports-reporter
공식 코드https://github.com/akskuchi/dhm-visual-storytelling
공식 코드https://github.com/akskuchi/groovist
공식 코드GROOViST: A Metric for Grounding Objects in Visual Storytelling
https://github.com/alibabaresearch/damo-convai
공식 코드Unifying Structured Data as Graph for Data-to-Text Pre-Training
https://github.com/alonsoapp/pixt3
공식 코드https://github.com/amazon-research/datatuner
공식 코드Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity
https://github.com/aplesner/flip-reasoning-challenge
공식 코드https://github.com/arjunakula/Visual-Discourse-Parsing
공식 코드https://github.com/arnozwang/esports-data-to-text
공식 코드Commentary Generation from Data Records of Multiplayer Strategy Esports Game
https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets
공식 코드Biomedical Data-to-Text Generation via Fine-Tuning Transformers
https://github.com/budzianowski/multiwoz
공식 코드Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
https://github.com/daehuikim/WikiOFGraph
공식 코드https://github.com/daniel3303/storyreasoning
공식 코드StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation
https://github.com/dcu-nlg/dcu-nlg-pbn
공식 코드https://github.com/deepmind/deepmind-research/tree/master/wikigraphs
공식 코드WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
https://github.com/dianaglzrico/neural-visual-storyteller
공식 코드https://github.com/diegma/graph-2-text
공식 코드Deep Graph Convolutional Encoders for Structured Data to Text Generation
https://github.com/drsy/pins
공식 코드Pruning Pre-trained Language Models with Principled Importance and Self-regularization
https://github.com/edillower/cyclenlg
공식 코드Faithful Low-Resource Data-to-Text Generation through Cycle Training
https://github.com/felix-last/kmeans_smote
공식 코드Oversampling for Imbalanced Learning Based on K-Means and SMOTE
https://github.com/francois-meyer/sspg
공식 코드https://github.com/francois-meyer/t2x
공식 코드https://github.com/fuzihaofzh/distant_supervision_nlg
공식 코드Partially-Aligned Data-to-Text Generation with Distant Supervision
https://github.com/fyyfu/semantic-watermark
공식 코드https://github.com/google-research-datasets/KELM-corpus
공식 코드Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training
https://github.com/google-research-datasets/ToTTo
공식 코드https://github.com/google-research/google-research
공식 코드Improving Compositional Generalization with Self-Training for Data-to-Text Generation
https://github.com/google-research/url-nlp
공식 코드TaTa: A Multilingual Table-to-Text Dataset for African Languages
https://github.com/ha-lins/DTG-SI
공식 코드https://github.com/hanane-djeddal/complex-answer-generation
공식 코드Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
https://github.com/haoningwu3639/StoryGen
공식 코드Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
https://github.com/harvardnlp/boxscore-data
공식 코드https://github.com/harvardnlp/data2text
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.