SOTAVerified

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

Showing 101–125 of 344 papers

TitleStatusHype
Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information—0
Conversation Style Transfer using Few-Shot Learning—0
Skit-S2I: An Indian Accented Speech to Intent datasetCode1
Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction—0
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasksCode0
The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competition—0
Zero-Shot Learning for Joint Intent and Slot Labeling—0
ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling—0
Multitask Learning for Low Resource Spoken Language Understanding—0
Introducing Semantics into Speech Encoders—0
Prompt Learning for Domain Adaptation in Task-Oriented Dialogue—0
Multilingual Name Entity Recognition and Intent Classification Employing Deep Learning Architectures—0
token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text—0
End-to-end Spoken Language Understanding with Tree-constrained Pointer GeneratorCode0
End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English—0
arXivEdits: Understanding the Human Revision Process in Scientific Writing—0
Learning Better Intent Representations for Financial Open Intent Classification—0
Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding—0
Augmenting Task-Oriented Dialogue Systems with Relation Extraction—0
Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR—0
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer EnsembleCode0
The Open-World Lottery Ticket Hypothesis for OOD Intent ClassificationCode0
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification—0
Knowledge Distillation Transfer Sets and their Impact on Downstream NLU Tasks—0
Explainable Abuse Detection as Intent Classification and Slot FillingCode0
Show:102550
← PrevPage 5 of 14Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TDT 0-8Accuracy (%)90.07—Unverified
2Partially Fine-tuned HuBERTAccuracy (%)87.51—Unverified
3Multi-SLURPAccuracy (%)78.33—Unverified
4Finstreder (Conformer)Accuracy (%)53.11—Unverified
5Finstreder (Quartznet)Accuracy (%)43.15—Unverified
#ModelMetricClaimedVerifiedStatus
1mT5 Base (encoder-only)Intent Accuracy86.1—Unverified
2mT5 Base (text-to-text)Intent Accuracy85.3—Unverified
3XLM-R BaseIntent Accuracy85.1—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-wwm-ext-baseAccuracy85.5—Unverified
#ModelMetricClaimedVerifiedStatus
1BERT (query + URL)F1-score0.77—Unverified