https://github.com/FDChongli/TwoWaysToImproveCSC
공식 코드Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
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/FairyFali/SLMs-Survey
공식 코드https://github.com/Fangjun-Li/SpatialLM-StepGame
공식 코드https://github.com/FederatedAI/FATE-LLM
공식 코드FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models
https://github.com/Felixgithub2017/CG-Eval
공식 코드Evaluating the Generation Capabilities of Large Chinese Language Models
https://github.com/Flitternie/CoreGen
공식 코드CoreGen: Contextualized Code Representation Learning for Commit Message Generation
https://github.com/FloatFrank/TIPA
공식 코드Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
https://github.com/FranxYao/Deep-Generative-Models-for-Natural-Language-Processing
공식 코드https://github.com/FranxYao/Gumbel-CRF
공식 코드https://github.com/FranxYao/dgm_latent_bow
공식 코드https://github.com/GT-SALT/FormalityStyleTransfer
공식 코드https://github.com/GU-DataLab/Chatbot-Auditing-Framework
공식 코드It is Time to Develop an Auditing Framework to Promote Value Aware Chatbots
https://github.com/GUIDesignResearch/GUIGAN
공식 코드GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
https://github.com/GXimingLu/a_star_neurologic
공식 코드NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
https://github.com/GanjinZero/BioBART
공식 코드BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model
https://github.com/Glaciohound/LM-Infinite
공식 코드LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
https://github.com/GreedyGeorge/COIN
공식 코드A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
https://github.com/GregorKobsik/Octree-Transformer
공식 코드Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences
https://github.com/Grenzlinie/MatTools
공식 코드MatTools: Benchmarking Large Language Models for Materials Science Tools
https://github.com/GuyTevet/SeqGAN-eval
공식 코드https://github.com/GuyTevet/diversity-eval
공식 코드Evaluating the Evaluation of Diversity in Natural Language Generation
https://github.com/HCPLab-SYSU/Medical_DS
공식 코드End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis
https://github.com/HKUNLP/instructor-embedding
공식 코드One Embedder, Any Task: Instruction-Finetuned Text Embeddings
https://github.com/HKUNLP/zerogen
공식 코드ZeroGen: Efficient Zero-shot Learning via Dataset Generation
https://github.com/HKUST-KnowComp/DISCOS-commonsense
공식 코드DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge
https://github.com/HLTCHKUST/CAiRE-COVID
공식 코드https://github.com/HLTCHKUST/PAML
공식 코드https://github.com/HLTCHKUST/sensational_headline
공식 코드Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning
https://github.com/HMEIatJHU/SelectiveGeneration
공식 코드What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
https://github.com/HanGuo97/soft-Q-learning-for-text-generation
공식 코드Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
https://github.com/HanNight/RE-T5
공식 코드https://github.com/HareeshBahuleyan/probabilistic_nlg
공식 코드Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation
https://github.com/HareeshBahuleyan/tf-var-attention
공식 코드https://github.com/Heidelberg-NLP/COINS
공식 코드COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion
https://github.com/Heidelberg-NLP/MFscore
공식 코드Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR
https://github.com/HendrikStrobelt/detecting-fake-text
공식 코드GLTR: Statistical Detection and Visualization of Generated Text
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.