mlsanityData to 7 Oct 2026

Intent Detection with WikiHow

arXiv 2009.05781 ↗First posted 12 Sep 2020cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

Modern task-oriented dialog systems need to reliably understand users' intents. Intent detection is most challenging when moving to new domains or new languages, since there is little annotated data. To address this challenge, we present a suite of pretrained intent detection models. Our models are able to predict a broad range of intended goals from many actions because they are trained on wikiHow, a comprehensive instructional website. Our models achieve state-of-the-art results on the Snips dataset, the Schema-Guided Dialogue dataset, and all 3 languages of the Facebook multilingual dialog datasets. Our models also demonstrate strong zero- and few-shot performance, reaching over 75% accuracy using only 100 training examples in all datasets.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 7; 2023: 5; 2024: 2; 2025: 1.

19 papers.

Sort:

By area:

  1. 2023Procedure-Aware Pretraining for Instructional Video Understandingcited by 48
  2. 2021Visual Goal-Step Inference using wikiHowcited by 42
  3. 2022Neuro-Symbolic Procedural Planning with Commonsense Promptingcited by 28
  4. 2021Effectiveness of Pre-training for Few-shot Intent Classificationcited by 27
  5. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 25
  6. 2023Causal Reasoning of Entities and Events in Procedural Textscited by 23
  7. 2022Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Datacited by 22
  8. 2022Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropizationcited by 19
  9. 2021Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manualscited by 18
  10. 2022Label Semantic Aware Pre-training for Few-shot Text Classificationcited by 18
  11. 2021DG2: Data Augmentation Through Document Grounded Dialogue Generationcited by 10
  12. 2022What Makes the Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generationcited by 8
7 more
  1. 2023NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processingcited by 8
  2. 2023OpenPI2.0: An Improved Dataset for Entity Tracking in Textscited by 8
  3. 2022Incorporating Task-specific Concept Knowledge into Script Learningcited by 3
  4. 2024PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Datasetcited by 3
  5. 2025InstructNet: A Novel Approach for Multi-Label Instruction Classification through Advanced Deep Learningcited by 2
  6. 2022Are All Steps Equally Important? Benchmarking Essentiality Detection of Eventscited by 1
  7. 2023Towards Flow Graph Prediction of Open-Domain Procedural Textscited by 0