Papers with Code 아카이브
Response Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 10
A task where an agent should play the $DE$ role and generate a text to respond to a $P$ message.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/AlignRM/RLFH
On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation
https://github.com/GraphGrailAi/DialoGPT
A Diversity-Promoting Objective Function for Neural Conversation Models
https://github.com/HuiyuanXie/tiage
https://github.com/JHU-CLSP/gpt2-narrative-decoding
https://github.com/KnightZhang625/BERT_TF
Unified Language Model Pre-training for Natural Language Understanding and Generation
https://github.com/LeonZh0u/Chatbot
Unified Language Model Pre-training for Natural Language Understanding and Generation
https://github.com/Liang-Qiu/SVRNN-dialogues
Structure Extraction in Task-Oriented Dialogues with Slot Clustering
https://github.com/MS-P3/code5/tree/main/gpt2
https://github.com/MindSpore-paper-code-3/code9/tree/main/mass
MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/MindSpore-scientific-2/code-12/tree/main/isr
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
https://github.com/MohdElgaar/DialogWAE
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
https://github.com/MoxinC/DST-SC
MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
https://github.com/PaddlePaddle/Knover/tree/develop/projects/Q-TOD
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/dialogue/plato-2
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt
https://github.com/SarthakVaswani/ace_bot
https://github.com/ShayekhBinIslam/openrag
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
https://github.com/ShiminLei/LA-Dialog-Generation-System
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
https://github.com/ShuoZhangXJTU/PEDP
MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
https://github.com/TaiseiAso/BiGruAttEncDec
A Simple, Fast Diverse Decoding Algorithm for Neural Generation
https://github.com/Tanasho0928/chat-oriented
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
https://github.com/Tanasho0928/ncm
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
https://github.com/UladzimirBaklan/qwerty
A Diversity-Promoting Objective Function for Neural Conversation Models
https://github.com/VachanVY/gpt.jax
https://github.com/WolfNiu/AdversarialDialogue
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
https://github.com/WolfNiu/polite-dialogue-generation
https://github.com/YunwenTechnology/Unilm
Unified Language Model Pre-training for Natural Language Understanding and Generation
https://github.com/aananda-giri/gpt2-nepali
https://github.com/abhaskumarsinha/Corpus2GPT
https://github.com/abhaskumarsinha/MinimalGPT
https://github.com/affjljoo3581/GPT2
https://github.com/agentica-project/verl-pipeline
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
https://github.com/akanyaani/gpt-2-tensorflow2.0
https://github.com/akanyaani/minGPTF
https://github.com/amarazad/DSRNet
Meta-Context Transformers for Domain-Specific Response Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.