Skip to content
This repository has been archived by the owner on May 31, 2023. It is now read-only.

Latest commit

 

History

History
62 lines (57 loc) · 4.88 KB

README.md

File metadata and controls

62 lines (57 loc) · 4.88 KB

Dialogue System

Paper collections for Dialogue System!! All bot can be divided into four parts, NLU, DM(DST & DP) and NLG.

Framework

  • [ACL 2020] Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment

Natural Language Understanding (NLU)

  • [SIGIR 2021] Pseudo Siamese Network for Few-shot Intent Generation
  • [EMNLP 2021] (paper) Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems

Slot Filling And Intent Induction

  • [ACL 2020] Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
  • [EACL 2021] (paper) Few-shot Learning for Slot Tagging with Attentive Relational Network
  • [EACL 2021] (paper) Few Shot Dialogue State Tracking using Meta-learning
  • [ACL 2021] Frustratingly Simple Few-Shot Slot Tagging
  • [EMNLP 2021] (paper) Robust Retrieval Augmented Generation for Zero-shot Slot Filling
  • [NAACL 2021] Few-shot Intent Classification and Slot Filling with Retrieved Examples
  • [ACL 2021] Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
  • [EMNLP 2019] (paper) Few-Shot Text Classification with Induction Network
    • Introduce dynamic routing to generate better class representations. One real industrial project.
  • [EMNLP/IJCNLP 2019] Hierarchical Attention Prototypical Networks for Few-Shot Text Classification
  • [NAACL 2021] Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System
  • [NAACL 2021] Knowledge Guided Metric Learning for Few-Shot Text Classification
  • [NAACL 2021] (paper) Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
  • [NIPS 2020] (paper) Uncertainty-aware Self-training for Few-shot Text Classification
  • [AAAI 2021] SALNet: Semi-Supervised Few-Shot Text Classification with Attention-Based Lexicon
  • [AAAI 2021] (paper) Does Head Label Help for Long-Tailed Multi-Label Text Classification
  • [ACL 2020] Dynamic Memory Induction Networks for Few-Shot Text Classification
    • result seems great
    • work follow the induction network, explicitly add dynamic memory model (constructed by base classes) to enhance "prototypes".
  • [ICLR 2020] Few-shot Text Classification with Distributional Signatures
  • [NIPS 2018] Attentive task-agnostic meta-learning for few-shot text classification
  • [EACL 2021] (paper) A Neural Few-Shot Text Classification Reality Check
  • [EACL 2021] Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference
  • [AAAI 2021] (paper) Few-Shot Learning for Multi-Label Intent Detection
  • [ACL 2021] Distinct Label Representations for Few-Shot Text Classification
  • [ACL 2021] Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
  • [ACL 2021] Don’t Miss the Labels: Label-semantic Augmented Meta-Learner for Few-Shot Text Classification
  • [ACL 2021] Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision
  • [EMNLP 2021] (paper) Nearest Neighbour Few-Shot Learning for Cross-lingual Classification
  • [IJCAI 2021] MEDA: Meta-Learning with Data Augmentation for Few-Shot Text Classification
  • [NAACL 2021] ConVEx: Data-Efficient and Few-Shot Slot Labeling
  • [EMNLP 2021] Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU
  • [EMNLP 2021] Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

Dialog Management

Dialog State Tracking

  • [EMNLP 2021] (paper) Effective Sequence-to-Sequence Dialogue State Tracking
  • [EMNLP 2021] Zero-Shot Dialogue State Tracking via Cross-Task Transfer

Policy

Natural Language Generation (NLG)

  • [EMNLP 2020] Composed Variational Natural Language Generation for Few-shot Intents
  • [ACL 2020] Few-Shot NLG with Pre-Trained Language Model
  • [ACL 2020] Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
  • [ACL 2021] AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation
  • [ACL 2021] On Training Instance Selection for Few-Shot Neural Text Generation
  • [ACL 2021] Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
  • [EMNLP 2021] (paper) Few-Shot Table-to-Text Generation with Prototype Memory
  • [EMNLP 2021] A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
  • [EMNLP 2021] (paper) Few-Shot Text Generation with Pattern-Exploiting Training