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/NetEase-FuXi/EET
공식 코드Easy and Efficient Transformer : Scalable Inference Solution For large NLP model
https://github.com/NetEase-GameAI/SARG
공식 코드SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
https://github.com/NicolasAG/convai
공식 코드https://github.com/NingMiao/CGMH
공식 코드CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
https://github.com/NingMiao/KerBS
공식 코드https://github.com/NingMiao/MC-tailor
공식 코드Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods
https://github.com/NohTow/PPL-MCTS
공식 코드https://github.com/PAIR-code/lit
공식 코드https://github.com/PKU-ONELab/Themis
공식 코드Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability
https://github.com/PStarH/long-seq-rwkv
공식 코드Enhancing RWKV-based Language Models for Long-Sequence Text Generation
https://github.com/PaddlePaddle/Knover
공식 코드PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
https://github.com/PaddlePaddle/PaddleNLP
공식 코드ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
https://github.com/PaddlePaddle/Research
공식 코드PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
https://github.com/PaddlePaddle/Research/tree/master/NLP/ACL2022-DuLeMon
공식 코드Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
https://github.com/Pascalson/Conditional-Seq-GANs
공식 코드Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
https://github.com/Pascalson/DyKGChat
공식 코드DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
https://github.com/Pascalson/LERG
공식 코드https://github.com/Pepper-lll/LMforImageGeneration
공식 코드Elucidating the design space of language models for image generation
https://github.com/PeritotZena/AI-vs-Angelou
공식 코드https://github.com/PlusLabNLP/Plot-guided-Coherence-Evaluation
공식 코드Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation
https://github.com/PlusLabNLP/story-gen-BART
공식 코드Content Planning for Neural Story Generation with Aristotelian Rescoring
https://github.com/PortNLP/FairEXTSummarizer
공식 코드Fair Summarization: Bridging Quality and Diversity in Extractive Summaries
https://github.com/QipengGuo/CycleGT
공식 코드Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
https://github.com/QwenLM/Self-Lengthen
공식 코드https://github.com/RUCAIBox/Few-Shot-KG2Text
공식 코드Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
https://github.com/RUCAIBox/TextBox
공식 코드TextBox: A Unified, Modularized, and Extensible Framework for Text Generation
https://github.com/RaghavSinghal10/fedex-lora
공식 코드FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models
https://github.com/Reason-Wang/ToolGen
공식 코드https://github.com/RefalMachine/llmtf_open
공식 코드Facilitating large language model Russian adaptation with Learned Embedding Propagation
https://github.com/RemiLeblond/SeaRNN-open
공식 코드https://github.com/RenaGao/LLMPirorknowledge
공식 코드Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
https://github.com/ReneeYe/VariationalTemplateMachine
공식 코드https://github.com/SHI-Labs/Rethinking-Text-Segmentation
공식 코드Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
https://github.com/SUTDNLP/ZGen
공식 코드https://github.com/Sachin19/seq2seq-con
공식 코드Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.