SOTAVerified|Agents Browse Leaderboard About

Intent Classification

Intent Classification is the task of correctly labeling a natural language utterance from a predetermined set of intents

Source: Multi-Layer Ensembling Techniques for Multilingual Intent Classification

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 151–160 of 344 papers

Title	Date	Tasks	Status	Hype
Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding	Oct 25, 2022	Data AugmentationDialogue Understanding	—Unverified	0
Augmenting Task-Oriented Dialogue Systems with Relation Extraction	Oct 24, 2022	intent-classificationIntent Classification	—Unverified	0
Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR	Oct 21, 2022	intent-classificationIntent Classification	—Unverified	0
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble	Oct 20, 2022	Contrastive Learningintent-classification	CodeCode Available	0
The Open-World Lottery Ticket Hypothesis for OOD Intent Classification	Oct 13, 2022	intent-classificationIntent Classification	CodeCode Available	0
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification	Oct 12, 2022	intent-classificationIntent Classification	—Unverified	0
Knowledge Distillation Transfer Sets and their Impact on Downstream NLU Tasks	Oct 10, 2022	domain classificationintent-classification	—Unverified	0
Explainable Abuse Detection as Intent Classification and Slot Filling	Oct 6, 2022	Abuse DetectionGeneral Classification	CodeCode Available	0
Domain- and Task-Adaptation for VaccinChatNL, a Dutch COVID-19 FAQ Answering Corpus and Classification Model	Oct 1, 2022	Chatbotintent-classification	—Unverified	0
Wizard of Tasks: A Novel Conversational Dataset for Solving Real-World Tasks in Conversational Settings	Oct 1, 2022	abstractive question answeringArticles	—Unverified	0

Show:10 25 50

← PrevPage 16 of 35Next →

All datasets SLURP MASSIVE KUAKE-QIC ORCAS-I

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TDT 0-8	Accuracy (%)	90.07	—	Unverified
2	Partially Fine-tuned HuBERT	Accuracy (%)	87.51	—	Unverified
3	Multi-SLURP	Accuracy (%)	78.33	—	Unverified
4	Finstreder (Conformer)	Accuracy (%)	53.11	—	Unverified
5	Finstreder (Quartznet)	Accuracy (%)	43.15	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mT5 Base (encoder-only)	Intent Accuracy	86.1	—	Unverified
2	mT5 Base (text-to-text)	Intent Accuracy	85.3	—	Unverified
3	XLM-R Base	Intent Accuracy	85.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-wwm-ext-base	Accuracy	85.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BERT (query + URL)	F1-score	0.77	—	Unverified