https://github.com/OriShapira/ENDow
공식 코드Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks
Papers with Code 아카이브
Dialogue
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 21
- 평가표
- 1
- 보존된 평가 기록
- 1
Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/PaddlePaddle/Knover
공식 코드https://github.com/PaddlePaddle/Knover/tree/develop/projects/AG-DST
공식 코드https://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/PolyAI-LDN/conversational-datasets
공식 코드https://github.com/Qatar-Computing-Research-Institute/dialectID
공식 코드https://github.com/RUCAIBox/TextBox
공식 코드TextBox 2.0: A Text Generation Library with Pre-trained Language Models
https://github.com/RenaGao/LLMPirorknowledge
공식 코드Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
https://github.com/SJY8460/SLM
공식 코드Do Large Language Model Understand Multi-Intent Spoken Language ?
https://github.com/SKTBrain/SUMBT
공식 코드SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
https://github.com/SLEEPWALKERG/LLM-DST-EVAL
공식 코드A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4
https://github.com/Sahandfer/CEM
공식 코드https://github.com/Sanyuan-Chen/C2C-DA
공식 코드C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
https://github.com/ServiceNow/research-workflow-discovery
공식 코드https://github.com/ShannonAI/OpenViDial
공식 코드OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
https://github.com/ShannonAI/backdoor_nlg
공식 코드Defending Against Backdoor Attacks in Natural Language Generation
https://github.com/SivilTaram/Persona-Dialogue-Generation
공식 코드You Impress Me: Dialogue Generation via Mutual Persona Perception
https://github.com/SmartDataAnalytics/kgirnet
공식 코드Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers
https://github.com/SpeechClub/SLIDE-demo
공식 코드SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation
https://github.com/TMMMU-Benchmark/evaluation
공식 코드VisTai: Benchmarking Vision-Language Models for Traditional Chinese in Taiwan
https://github.com/TeddLi/Disentangle
공식 코드DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
https://github.com/ToLightUpTheSky/ParsingDST
공식 코드https://github.com/Tomiinek/MultiWOZ_Evaluation
공식 코드https://github.com/Vernacular-ai/N-Best-ASR-Transformer
공식 코드N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses
https://github.com/WolfNiu/AutoAugDialogue
공식 코드Automatically Learning Data Augmentation Policies for Dialogue Tasks
https://github.com/WoodScene/RoS
공식 코드Continual Dialogue State Tracking via Reason-of-Select Distillation
https://github.com/WoodScene/TaSL
공식 코드TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
https://github.com/XiaoxiaoGuo/fashion-retrieval
공식 코드https://github.com/ZhangYiqun018/StickerConv
공식 코드STICKERCONV: Generating Multimodal Empathetic Responses from Scratch
https://github.com/a-rain/state_management_empdialogue
공식 코드https://github.com/aalto-speech/slurpfood
공식 코드Out-of-distribution generalisation in spoken language understanding
https://github.com/aarontengdechuan/pro-han
공식 코드Pro-HAN: A Heterogeneous Graph Attention Network for Profile-Based Spoken Language Understanding
https://github.com/abaheti95/toxichat
공식 코드Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.