https://github.com/mhackiori/agir
공식 코드AGIR: Automating Cyber Threat Intelligence Reporting with Natural Language Generation
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/mhagiwara/github-typo-corpus
공식 코드GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors
https://github.com/mhh0318/unid3
공식 코드Unified Discrete Diffusion for Simultaneous Vision-Language Generation
https://github.com/michael-mersinias/nli_text_generation
공식 코드https://github.com/michael-wzhu/PromptCBLUE
공식 코드PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain
https://github.com/michaelzhouwang/sequence_span_rewriting
공식 코드Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
https://github.com/michelalorandi/d2t-gen-for-under-res-lang-w-llms
공식 코드https://github.com/michigannlp/dynaopt
공식 코드Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation
https://github.com/michigannlp/task-adaptive_tokenization
공식 코드Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond
https://github.com/microsoft/CodeBERT
공식 코드CodeBERT: A Pre-Trained Model for Programming and Natural Languages
https://github.com/microsoft/DeBERTa
공식 코드Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
https://github.com/microsoft/DeepSpeed
공식 코드The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models
https://github.com/microsoft/EA-VQ-VAE
공식 코드Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder
https://github.com/microsoft/FLAML
공식 코드Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference
https://github.com/microsoft/HaDes
공식 코드A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
https://github.com/microsoft/MASS
공식 코드MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/microsoft/MixingBoard
공식 코드MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform
https://github.com/microsoft/ProphetNet
공식 코드https://github.com/microsoft/RadFact
공식 코드https://github.com/microsoft/TaskTracker
공식 코드Get my drift? Catching LLM Task Drift with Activation Deltas
https://github.com/microsoft/UniTAB
공식 코드UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
https://github.com/microsoft/advnlg
공식 코드Joint Generator-Ranker Learning for Natural Language Generation
https://github.com/microsoft/biogpt
공식 코드BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
https://github.com/microsoft/dataflow2text
공식 코드https://github.com/microsoft/deepspeed-mii
공식 코드DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
https://github.com/microsoft/defacto
공식 코드On Improving Summarization Factual Consistency from Natural Language Feedback
https://github.com/microsoft/document-level-targeted-content-transfer
공식 코드Substance over Style: Document-Level Targeted Content Transfer
https://github.com/microsoft/dp-transformers
공식 코드Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
https://github.com/microsoft/efficientlongsequencemodeling
공식 코드Efficient Long Sequence Modeling via State Space Augmented Transformer
https://github.com/microsoft/fastseq
공식 코드https://github.com/microsoft/glge
공식 코드GLGE: A New General Language Generation Evaluation Benchmark
https://github.com/microsoft/gpt-mt
공식 코드How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
https://github.com/microsoft/hitab
공식 코드HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation
https://github.com/microsoft/kid
공식 코드https://github.com/microsoft/lmops
공식 코드In-Context Demonstration Selection with Cross Entropy Difference
https://github.com/microsoft/mars
공식 코드MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.