https://github.com/huawei-noah/Pretrained-Language-Model
공식 코드PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model
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/huawei-noah/Pretrained-Language-Model/tree/master/PMLM
공식 코드Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order
https://github.com/huawei-noah/kd-nlp
공식 코드https://github.com/huawei-noah/noah-research
공식 코드Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
https://github.com/huggingface/nn_pruning
공식 코드What Matters In The Structured Pruning of Generative Language Models?
https://github.com/huggingface/transformers
공식 코드HuggingFace's Transformers: State-of-the-art Natural Language Processing
https://github.com/hughplay/vtt
공식 코드https://github.com/huseyinatahaninan/differentially-private-fine-tuning-of-language-models
공식 코드https://github.com/hustvl/omnimamba
공식 코드OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
https://github.com/hvision-nku/storydiffusion
공식 코드StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
https://github.com/hwanheelee1993/UMIC
공식 코드UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
https://github.com/hy-zhao23/gcs
공식 코드Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
https://github.com/hyn2028/llm-cxr
공식 코드LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
https://github.com/hypasd-art/etapp
공식 코드Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
https://github.com/hyperconnect/sem-ent
공식 코드Measuring and Improving Semantic Diversity of Dialogue Generation
https://github.com/hyunseoklee-ai/remodetect
공식 코드ReMoDetect: Reward Models Recognize Aligned LLM's Generations
https://github.com/hyunseoklee-ai/reward_llm_detect
공식 코드ReMoDetect: Reward Models Recognize Aligned LLM's Generations
https://github.com/hyx1999/sam-decoding
공식 코드https://github.com/hzfinfdu/diffusion-bert
공식 코드DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
https://github.com/iaar-shanghai/ctgsurvey
공식 코드Controllable Text Generation for Large Language Models: A Survey
https://github.com/iaar-shanghai/datg
공식 코드Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
https://github.com/iai-group/usersimcrs
공식 코드UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems
https://github.com/iakovosevdaimon/greekbart
공식 코드GreekBART: The First Pretrained Greek Sequence-to-Sequence Model
https://github.com/iakovosevdaimon/greeksum
공식 코드GreekBART: The First Pretrained Greek Sequence-to-Sequence Model
https://github.com/ianarawjo/ChainForge
공식 코드ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
https://github.com/ibm/auto-contrastive-generation
공식 코드The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers
https://github.com/ibm/quality-controlled-paraphrase-generation
공식 코드https://github.com/ibm/regression-transformer
공식 코드https://github.com/ibm/reprogbert
공식 코드Reprogramming Pretrained Language Models for Antibody Sequence Infilling
https://github.com/icannos/glimpse-mds
공식 코드GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
https://github.com/ictmldm/FPG
공식 코드https://github.com/ictmldm/SCAPE
공식 코드Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation
https://github.com/ictnlp/DialoFlow
공식 코드Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances
https://github.com/ictnlp/LSG
공식 코드Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation
https://github.com/ictnlp/bayling
공식 코드https://github.com/ictnlp/semling-mnmt
공식 코드Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.