No star if cite number is below 10; one stars if cite number is below 100; two stars if cite number is below 1000; three stars if cite number is below 5000; four stars if cite number is below 10000; five stars if cite number exceed 10000. For example, DialoGPT have been cited 892 times (before April 28th, 2023) and it should be marked as two stars.
No star if github or gitee stars is below 100; one stars if github or gitee stars are below 1K; two stars if github or gitee stars is below 10K; three stars if github or gitee stars are below 50K; four stars if github or gitee stars are below 100K; five stars if github or gitee stars exceed 1M. For example, https://github.com/openai/chatgpt-retrieval-plugin has 15.2K stars (before April 28th, 2023) and it should be marked as three stars.
- Dialog Papers
- Evaluators
- Multi-modal
- New Evaluator
- ...
+ new content
+ Dialogue & Question Answering Evaluator
- detele content-
-
- [DialoGPT(ACL2020)--DIALOGPT:Large-Scale Generative Pre-training for Conversational Response Generation] (https://arxiv.org/abs/1911.00536) ⭐⭐
- [FusedChat--Fusing Task-Oriented and Open-Domain Dialogues in Conversational Agents] 2022-06-28 (https://ojs.aaai.org/index.php/AAAI/article/view/21416) ⭐
- [EVA2.0--EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training] 2023 (https://link.springer.com/article/10.1007/s11633-022-1387-3) ⭐
- [HOPE--Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations] 2022-02 (https://dl.acm.org/doi/abs/10.1145/3488560.3498509) ⭐
- [TOD turnsTOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue] 2020 (https://arxiv.org/abs/2004.06871) ⭐⭐
- [LAION-400_2021--LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs] 2021 (https://arxiv.org/abs/2111.02114) ⭐⭐
- [Crosswoz--CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset] 2020 (https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00314/96453/CrossWOZ-A-Large-Scale-Chinese-Cross-Domain-Task) ⭐
- Search-engine-augmented dialogue response generation with cheaply supervised query production 2023-04
-
-
-
- Robustness testing of language understanding in task-oriented dialog⭐
- SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding⭐
- Space-3: Unified dialog model pre-training for task-oriented dialog understanding and generation
- Natural language understanding for task oriented dialog in the biomedical domain in a low resources context
- Proactive Human-Machine Conversation with Explicit Conversation Goals
-
- Continual learning for natural language generation in task-oriented dialog systems⭐
- Efficient retrieval augmented generation from unstructured knowledge for task-oriented dialog⭐
- Galaxy: A generative pre-trained model for task-oriented dialog with semi-supervised learning and explicit policy injection⭐
- Recent advances and challenges in task-oriented dialog systems⭐⭐
- PRAL: A tailored pre-training model for task-oriented dialog generation⭐
- MuTual: A Dataset for Multi-Turn Dialogue Reasoning⭐
- NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation
-
-
-
- Snips⭐⭐⭐⭐
- MIT Restaurant Corpus⭐⭐
- MIT Movie Corpus⭐⭐⭐
- frames⭐⭐⭐
- WOZ⭐⭐⭐
- DuConv
-
- Multimodal Dialogs (MMD) Dataset⭐
- Facebook Multilingual Task Oriented Dataset⭐⭐⭐
- [MMD: Towards Building Large Scale Multimodal Domain-Aware Conversation Systems(https://amritasaha1812.github.io/MMD/)]
(https://github.com/amritasaha1812/MMD_Code)
-
-
-
- "TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue"
- Soloist: Building task bots at scale with transfer learning and machine teaching. TACL 2021
- UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2. AAAI 2021
- Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation
- Task-Oriented Dialogue System as Natural Language Generation
-
-
Generative Model
-
Paper
-
Model
-
Metrics
-
Correlation between Automated Evaluation Scores and Human Judgement
-
Spearman Correlation
-
Pearson Correlation
-
-
-
Human Evaluation
-
Automated Evaluation Metrics
-
$\color{Cyan}Multi\color{teal}-\color{orange}modal$
-
