https://github.com/SalesforceAIResearch/Unlocking-TextGen
공식 코드Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
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/Sampreeth-sarma/T5-ABSA-Summarization
공식 코드Exploring Conditional Text Generation for Aspect-Based Sentiment Analysis
https://github.com/SeoroMin/Prompt4LLM-Eval
공식 코드Which is better? Exploring Prompting Strategy For LLM-based Metrics
https://github.com/ShannonAI/OpenViDial
공식 코드OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
https://github.com/ShannonAI/backdoor_nlg
공식 코드Defending Against Backdoor Attacks in Natural Language Generation
https://github.com/ShaojieJiang/tldr
공식 코드TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
https://github.com/Shark-NLP/DiffuSeq
공식 코드DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
https://github.com/ShoumikSaha/ai-polished-text
공식 코드Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing
https://github.com/SiavashShams/neuro2semantic
공식 코드https://github.com/Simonlee711/MEME
공식 코드Emergency Department Decision Support using Clinical Pseudo-notes
https://github.com/SivilTaram/Persona-Dialogue-Generation
공식 코드You Impress Me: Dialogue Generation via Mutual Persona Perception
https://github.com/SkAndMl/gpt-variations
공식 코드Towards smaller, faster decoder-only transformers: Architectural variants and their implications
https://github.com/SmartDataAnalytics/kgirnet
공식 코드Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers
https://github.com/Soistesimmer/AMR-multiview
공식 코드Structural Information Preserving for Graph-to-Text Generation
https://github.com/Soldelli/MAD
공식 코드https://github.com/SourcecodeSharing/CWSpostediting
공식 코드Neural Chinese Word Segmentation as Sequence to Sequence Translation
https://github.com/SpectData/MONAH
공식 코드MONAH: Multi-Modal Narratives for Humans to analyze conversations
https://github.com/SpeechClub/SLIDE-demo
공식 코드SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation
https://github.com/StonyBrookNLP/SLDS-Stories
공식 코드https://github.com/Stry233/Visual-Story-Generation-Based-on-Emotional-and-Keyword-Scheme
공식 코드https://github.com/SuperSupermoon/MedViLL
공식 코드https://github.com/TAMU-VITA/ShapeMatchingGAN
공식 코드Controllable Artistic Text Style Transfer via Shape-Matching GAN
https://github.com/THU-KEG/TWAG
공식 코드https://github.com/THUDM/InversePrompting
공식 코드Controllable Generation from Pre-trained Language Models via Inverse Prompting
https://github.com/THUDM/KBRD
공식 코드https://github.com/THUDM/KOBE
공식 코드Towards Knowledge-Based Personalized Product Description Generation in E-commerce
https://github.com/THUNLP-MT/TRICE
공식 코드Transfer Learning for Sequence Generation: from Single-source to Multi-source
https://github.com/THUcqb/KOBE
공식 코드Towards Knowledge-Based Personalized Product Description Generation in E-commerce
https://github.com/TIGER-AI-Lab/TIGERScore
공식 코드TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
https://github.com/TMMMU-Benchmark/evaluation
공식 코드VisTai: Benchmarking Vision-Language Models for Traditional Chinese in Taiwan
https://github.com/TXH-mercury/VALOR
공식 코드VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
https://github.com/TalSchuster/VitaminC
공식 코드Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence
https://github.com/TaoZhen1110/CUDRT_Benchmark
공식 코드Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
https://github.com/TechnicolorGUO/InteractiveSurvey
공식 코드InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System
https://github.com/TengShi-RUC/CFRAG
공식 코드Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation
https://github.com/ThiagoCF05/webnlg
공식 코드Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.