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 231240 of 344 papers

TitleStatusHype
The impact of domain-specific representations on BERT-based multi-domain spoken language understanding0
Industry Scale Semi-Supervised Learning for Natural Language Understanding0
NUBOT: Embedded Knowledge Graph With RASA Framework for Generating Semantic Intents Responses in Roman Urdu0
Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification0
Neural Data Augmentation via Example ExtrapolationCode0
Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR TranscriptCode1
ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification0
A survey of joint intent detection and slot-filling models in natural language understanding0
A character representation enhanced on-device Intent Classification0
Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection0
Show:102550
← PrevPage 24 of 35Next →

Benchmark Results

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