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/zeaver/multifactor
공식 코드Improving Question Generation with Multi-level Content Planning
https://github.com/zehui127/latent-dna-diffusion
공식 코드https://github.com/zeinsh/lenta_short_sentences
공식 코드https://github.com/zeng-wh/seen-to-unseen
공식 코드https://github.com/zenquiorra/m3ls
공식 코드https://github.com/zequnl/CMAML
공식 코드Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
https://github.com/zequnl/graphex
공식 코드Graphine: A Dataset for Graph-aware Terminology Definition Generation
https://github.com/zequnl/metafill
공식 코드MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks
https://github.com/zgahhblhc/Debiased-Chat
공식 코드Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning
https://github.com/zh-wang-med/llm-rg4
공식 코드LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts
https://github.com/zhangbo-nlp/kedit
공식 코드Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
https://github.com/zhangbo-nlp/vikdf
공식 코드https://github.com/zhangbo-nlp/zrigf
공식 코드ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
https://github.com/zhanghainan/ReCoSa
공식 코드ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
https://github.com/zhangjf-nlp/LatentDPO
공식 코드https://github.com/zhaochaocs/planned-ptm
공식 코드Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach
https://github.com/zhaoxlpku/KnowledGPT
공식 코드Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
https://github.com/zhaoyiran924/adv-in-context-learning
공식 코드https://github.com/zhaoyucs/vsd
공식 코드Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation
https://github.com/zhenchenwan/ted-viton
공식 코드TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On
https://github.com/zhenwang9102/coherence-boosting
공식 코드Coherence boosting: When your pretrained language model is not paying enough attention
https://github.com/zhi-xuan-chen/reg2rg
공식 코드Large Language Model with Region-guided Referring and Grounding for CT Report Generation
https://github.com/zhijie-group/unicms
공식 코드UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding
https://github.com/zhijing-jin/IMT
공식 코드IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
https://github.com/zhijing-jin/IMaT
공식 코드IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
https://github.com/zhijing-jin/Text_Style_Transfer_Survey
공식 코드https://github.com/zhiyuan-gg/conformal-uncertainty-criterion
공식 코드ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees
https://github.com/zhjgao/difformer
공식 코드Empowering Diffusion Models on the Embedding Space for Text Generation
https://github.com/zhjohnchan/R2Gen
공식 코드https://github.com/zhjohnchan/R2GenCMN
공식 코드https://github.com/zhjohnchan/ptunifier
공식 코드Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts
https://github.com/zhongping-zhang/engine
공식 코드Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval
https://github.com/zhourobotics/reasondrive
공식 코드https://github.com/zhouzhouyang520/empatheticdialoguegeneration_escm
공식 코드Exploiting Emotion-Semantic Correlations for Empathetic Response Generation
https://github.com/zhuang-li/vae-dprior
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.