https://github.com/Henry-E/surface-realization-shallow-task
공식 코드Shape of synth to come: Why we should use synthetic data for English surface realization
Papers with Code 아카이브
Text Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 25
- 평가표
- 155
- 보존된 평가 기록
- 54
Text Generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task is more formally known as "natural language generation" in the literature.
Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU.
Further readings:
<span style="color:grey; opacity: 0.6">( Image credit: Adversarial Ranking for Language Generation )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/HenryJunW/TAG
공식 코드TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
https://github.com/Holmeswww/PPOGAN
공식 코드Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
https://github.com/HongshengHu/membership-inference-machine-learning-literature
공식 코드https://github.com/IAAR-Shanghai/UHGEval
공식 코드https://github.com/IAmS4n/DGSAN
공식 코드https://github.com/IAmS4n/TextGenerationEvaluationMetrics
공식 코드Jointly Measuring Diversity and Quality in Text Generation Models
https://github.com/IBM/GPT-too-AMR2text
공식 코드GPT-too: A language-model-first approach for AMR-to-text generation
https://github.com/IBM/Graph2Seq
공식 코드Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
https://github.com/IBM/SQL-to-Text
공식 코드https://github.com/IBM/regen
공식 코드https://github.com/IDEA-XL/RAPM
공식 코드Rethinking Text-based Protein Understanding: Retrieval or LLM?
https://github.com/IIT-PAVIS/Positional_Diffusion
공식 코드Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models
https://github.com/INK-USC/hypter
공식 코드Learning to Generate Task-Specific Adapters from Task Description
https://github.com/IlyaGusev/summarus
공식 코드Importance of Copying Mechanism for News Headline Generation
https://github.com/ImKeTT/ZeroGen
공식 코드ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles
https://github.com/ImKeTT/adavae
공식 코드AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling
https://github.com/ImperialNLP/BertGen
공식 코드https://github.com/ImperialNLP/pysimt
공식 코드Exploring Supervised and Unsupervised Rewards in Machine Translation
https://github.com/Isaac-theori/PCJailbreak
공식 코드BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models
https://github.com/Jacob-Zhou/simple-csc
공식 코드https://github.com/JasonObeid/Chart2Text
공식 코드Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model
https://github.com/JianGuanTHU/StoryEndGen
공식 코드Story Ending Generation with Incremental Encoding and Commonsense Knowledge
https://github.com/JiancongXiao/PM_RLHF
공식 코드https://github.com/JindongGu/Awesome-Prompting-on-Vision-Language-Model
공식 코드A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models
https://github.com/Jiuzhouh/Multi-Score
공식 코드https://github.com/JunjieHu/ReCo-RL
공식 코드What Makes A Good Story? Designing Composite Rewards for Visual Storytelling
https://github.com/Jxu-Thu/DITTO
공식 코드Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
https://github.com/K-H-Ismail/torchortho
공식 코드https://github.com/KaijuML/PARENTing-rl
공식 코드https://github.com/KaijuML/data-to-text-hierarchical
공식 코드https://github.com/KaijuML/dtt-multi-branch
공식 코드Controlling Hallucinations at Word Level in Data-to-Text Generation
https://github.com/Kim-Minseon/APGP
공식 코드Automatic Jailbreaking of the Text-to-Image Generative AI Systems
https://github.com/LAMDA-RL/CoLA
공식 코드https://github.com/LARC-CMU-SMU/Enconter
공식 코드ENCONTER: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer
https://github.com/LARC-CMU-SMU/RecipeGPT-exp
공식 코드RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.