Skip to content

Latest commit

 

History

History
71 lines (63 loc) · 9.33 KB

domain-intent-slot.md

File metadata and controls

71 lines (63 loc) · 9.33 KB

NLU papers for domain-intent-slot

A list of recent papers regarding natural language understanding and spoken language understanding.
It contains sequence labelling, sentence classification, dialogue act classification, dialogue state tracking and so on.

  • A review about NLU datasets for task-oriented dialogue is here.
  • There is an implementation of joint training of slot filling and intent detection for NLU, which is evaluated on ATIS, SNIPS, the Facebook’s multilingual dataset, MIT corpus, E-commerce Shopping Assistant (ECSA) dataset and CoNLL2003 NER datasets.

Bookmarks

1 Variant networks for different semantic representations

1.1 Domain-intent-slot

1.2 Dialogue act (act-slot-value triples)

1.3 Hierarchical Representations

2 Robustness to ASR-error

3 Zero-shot learning and domain adaptation

3.1 Zero-shot learning

3.2 Few-shot learning

3.3 Domain adaptation

3.3 Meta-learning

  • Investigating Meta-Learning Algorithms for Low-Resource NLU tasks. Zi-Yi Dou, Keyi Yu, Antonios Anastasopoulos. EMNLP 2019[short]. [pdf]
  • Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources. Qianhui Wu, Zijia Lin, Guoxin Wang, Hui Chen, Börje F. Karlsson, Biqing Huang, Chin-Yew Lin. AAAI 2020. [pdf]