mlsanityData to 7 Oct 2026

Few-shot Learning for Slot Tagging with Attentive Relational Network

arXiv 2103.02333 ↗First posted 3 Mar 2021cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Metric-based learning is a well-known family of methods for few-shot learning, especially in computer vision. Recently, they have been used in many natural language processing applications but not for slot tagging. In this paper, we explore metric-based learning methods in the slot tagging task and propose a novel metric-based learning architecture - Attentive Relational Network. Our proposed method extends relation networks, making them more suitable for natural language processing applications in general, by leveraging pretrained contextual embeddings such as ELMO and BERT and by using attention mechanism. The results on SNIPS data show that our proposed method outperforms other state-of-the-art metric-based learning methods.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

27 of 37 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2018Deep contextualized word representationscited by 2,285
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  9. 2019A Closer Look at Few-shot Classificationcited by 679
  10. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
  11. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  12. 2017Advances in Pre-Training Distributed Word Representationscited by 207
15 more
  1. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  2. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  3. 2018Learn To Pay Attentioncited by 83
  4. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  5. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  6. 2019Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Taskscited by 48
  7. 2017Towards Zero-Shot Frame Semantic Parsing for Domain Scalingcited by 40
  8. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  9. 2016Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Fillingcited by 25
  10. 2018Zero-Shot Adaptive Transfer for Conversational Language Understandingcited by 20
  11. 2017Neural Models for Sequence Chunkingcited by 10
  12. 2016Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understandingcited by 9
  13. 2015Recurrent Neural Networks with External Memory for Language Understandingcited by 6
  14. 2016Domain Adaptation of Recurrent Neural Networks for Natural Language Understandingcited by 5
  15. 2017Concept Transfer Learning for Adaptive Language Understandingcited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 1.

6 papers.

  1. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  2. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  3. 2023Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuningcited by 4
  4. 2021Few-shot Named Entity Recognition with Cloze Questionscited by 1
  5. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  6. 2023Actively Discovering New Slots for Task-oriented Conversationcited by 0