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/ml-jku/EVA
공식 코드Parameter Efficient Fine-tuning via Explained Variance Adaptation
https://github.com/ml-jku/SDLG
공식 코드Semantically Diverse Language Generation for Uncertainty Estimation in Language Models
https://github.com/ml-jku/hopfield-layers
공식 코드https://github.com/ml-postech/selective-generation
공식 코드https://github.com/ml-research/SCAR
공식 코드SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
https://github.com/ml-stat-sustech/local-perplexity-ranking
공식 코드On the Noise Robustness of In-Context Learning for Text Generation
https://github.com/mlai-yonsei/exceptionalbenchmark
공식 코드Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation
https://github.com/mlgroupjlu/rwkv-survey
공식 코드https://github.com/mlo-lab/bvcd_generative_models
공식 코드A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
https://github.com/mlvlab/llamo
공식 코드https://github.com/mmiao2/Hallucination
공식 코드Hallucination, Monofacts, and Miscalibration: An Empirical Investigation
https://github.com/mmurrad/eeg-to-text
공식 코드EEG-to-Text Translation: A Model for Deciphering Human Brain Activity
https://github.com/mnhng/HeadFilt
공식 코드https://github.com/mnschmit/unsupervised-graph-text-conversion
공식 코드An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing
https://github.com/mohit2b/ecosage
공식 코드An EcoSage Assistant: Towards Building A Multimodal Plant Care Dialogue Assistant
https://github.com/moinnadeem/characterizing-sampling-algorithms
공식 코드A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
https://github.com/mollyshuu/rezg
공식 코드ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speech
https://github.com/monisha-jega/paraphrasing_embedding_outputs
공식 코드Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
https://github.com/mooler0410/llmspracticalguide
공식 코드Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
https://github.com/moonlight-syntax/luna
공식 코드LUNA: A Framework for Language Understanding and Naturalness Assessment
https://github.com/moritzlaurer/zeroshot-classifier
공식 코드Building Efficient Universal Classifiers with Natural Language Inference
https://github.com/morningmoni/GAR
공식 코드Generation-Augmented Retrieval for Open-domain Question Answering
https://github.com/morningmoni/LCGen-eval
공식 코드https://github.com/morningmoni/RL-MMR
공식 코드Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning
https://github.com/morningmoni/citesum
공식 코드https://github.com/morningmoni/ede
공식 코드https://github.com/moussakam/frugalscore
공식 코드FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation
https://github.com/moxmiller/counterfactual-reasoning
공식 코드Counterfactual reasoning: an analysis of in-context emergence
https://github.com/mozerwang/demo
공식 코드DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
https://github.com/mozhu621/SGT
공식 코드LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
https://github.com/mozhu621/longgenbench
공식 코드LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
https://github.com/mozhu621/superwriter
공식 코드SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models
https://github.com/mr0223/adaptive_lora_merge
공식 코드Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation
https://github.com/mrflogs/LoRA-Pro
공식 코드https://github.com/mrzhengxin/ctg-regex-instruction
공식 코드Toward Unified Controllable Text Generation via Regular Expression Instruction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.