Intent Detection

Intent Detection is a task of determining the underlying purpose or goal behind a user's search query given a context. The task plays a significant role in search and recommendations. A traditional approach for intent detection implies using an intent detector model to classify user search query into predefined intent categories, given a context. One of the key challenges of the task implies identifying user intents for cold-start sessions, i.e., search sessions initiated by a non-logged-in or unrecognized user.

Source: Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 276–300 of 330 papers

Title	Date	Tasks	Status
Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection	Jan 7, 2025	Intent DetectionNatural Language Understanding	CodeCode Available
Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence	Dec 1, 2022	Graph Neural NetworkIntent Detection	CodeCode Available
Spoken Language Intent Detection using Confusion2Vec	Apr 7, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available
Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets	May 28, 2023	Intent DetectionNatural Language Understanding	CodeCode Available
Question Embeddings Based on Shannon Entropy: Solving intent classification task in goal-oriented dialogue system	Mar 25, 2019	General Classificationintent-classification	CodeCode Available
Learning Multimodal AI Algorithms for Amplifying Limited User Input into High-dimensional Control Space	May 16, 2025	Deep Reinforcement LearningIntent Detection	CodeCode Available
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks	Dec 16, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available
HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding	Jan 5, 2023	Data AugmentationIntent Detection	CodeCode Available
MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU	Aug 15, 2024	domain classificationIntent Detection	CodeCode Available
HPERL: 3D Human Pose Estimation from RGB and LiDAR	Oct 16, 2020	3D Human Pose EstimationAction Recognition	CodeCode Available
SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU	Nov 16, 2023	Intent DetectionNatural Language Understanding	CodeCode Available
Churn Intent Detection in Multilingual Chatbot Conversations and Social Media	Aug 25, 2018	ChatbotIntent Detection	CodeCode Available
Effectiveness of Pre-training for Few-shot Intent Classification	Sep 13, 2021	Classificationintent-classification	CodeCode Available
Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study	Jan 7, 2025	intent-classificationIntent Classification	CodeCode Available
“Where is My Parcel?” Fast and Efficient Classifiers to Detect User Intent in Natural Language	Dec 16, 2019	English Conversational Speech RecognitionIntent Detection	CodeCode Available
Towards Multi-label Unknown Intent Detection	Oct 1, 2022	Intent Detection	CodeCode Available
ReCoMIF: Reading comprehension based multi-source information fusion network for Chinese spoken language understanding	Aug 1, 2023	Intent DetectionMultiple-choice	CodeCode Available
ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction	Oct 8, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available
Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling	Oct 1, 2022	Intent DetectionSemantic Frame Parsing	CodeCode Available
Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Filling	Sep 9, 2022	Graph AttentionIntent Detection	CodeCode Available
Representation based meta-learning for few-shot spoken intent recognition	Jun 29, 2021	Classificationintent-classification	CodeCode Available
Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection	Oct 6, 2020	Few-Shot LearningGeneralized Few-Shot Learning	CodeCode Available
A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling	Dec 26, 2018	Decoder	CodeCode Available
Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts	Apr 19, 2019	Intent Detection	CodeCode Available
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework	Jun 10, 2025	Domain AdaptationIntent Detection	CodeCode Available

Show:10 25 50

← PrevPage 12 of 14Next →

All datasets ATIS MixSNIPS MixATIS SNIPS ASOS.com user intent BANKING77 ATIS (vi)BANKING77 10-shot BANKING77 5-shot CAIS CLINC150 CLINC150 10-shot

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Bi-model with decoder	Accuracy	98.99	—	Unverified
2	Transformer-Capsule	Accuracy	98.89	—	Unverified
3	Attention Encoder-Decoder NN	Accuracy	98.43	—	Unverified
4	Joint model with recurrent slot label context	Accuracy	98.4	—	Unverified
5	CTRAN	Accuracy	98.07	—	Unverified
6	Joint BERT + CRF	Accuracy	97.9	—	Unverified
7	SF-ID (BLSTM) network	Accuracy	97.76	—	Unverified
8	SF-ID	Accuracy	97.76	—	Unverified
9	JointBERT-CAE	Accuracy	97.5	—	Unverified
10	Stack-Propagation (+BERT)	Accuracy	97.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SSRAN	Accuracy	98.4	—	Unverified
2	BiSLU	Accuracy	97.8	—	Unverified
3	DGIF	Accuracy	97.8	—	Unverified
4	TFMN	Accuracy	97.7	—	Unverified
5	Co-guiding Net	Accuracy	97.7	—	Unverified
6	TFMN (PACL)	Accuracy	97.4	—	Unverified
7	MISCA	Accuracy	97.3	—	Unverified
8	Uni-MIS	Accuracy	97.2	—	Unverified
9	SLIM	Accuracy	97.2	—	Unverified
10	SLIM (PACL)	Accuracy	96.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DGIF	Accuracy	83.3	—	Unverified
2	UGEN	Accuracy	83	—	Unverified
3	TFMN (PACL)	Accuracy	82.9	—	Unverified
4	SLIM (PACL)	Accuracy	81.9	—	Unverified
5	BiSLU	Accuracy	81.5	—	Unverified
6	TFMN	Accuracy	79.8	—	Unverified
7	Co-guiding Net	Accuracy	79.1	—	Unverified
8	RoBERTa (PACL)	Accuracy	79.1	—	Unverified
9	Uni-MIS	Accuracy	78.5	—	Unverified
10	SLIM	Accuracy	78.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CTRAN	Accuracy	99.42	—	Unverified
2	Stack-Propagation (+BERT)	Accuracy	99	—	Unverified
3	JointBERT-CAE	Accuracy	98.3	—	Unverified
4	AGIF	Accuracy	98.1	—	Unverified
5	LIDSNet	Accuracy	98	—	Unverified
6	Stack-Propagation	Accuracy	98	—	Unverified
7	SF-ID	Accuracy	97.43	—	Unverified
8	SF-ID (BLSTM) network	Accuracy	97.43	—	Unverified
9	Capsule-NLU	Accuracy	97.3	—	Unverified
10	Slot-Gated BLSTM with Attension	Accuracy	97	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	plain-LSTM	F1	0.89	—	Unverified
2	linear-Ngrams	F1	0.87	—	Unverified
3	glove-LSTM	F1	0.86	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	94.42	—	Unverified
2	OCaTS (kNN-GPT-4)	Accuracy (%)	82.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	JointBERT-CAE	Intent Accuracy	97.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	89.79	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	84.01	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CM-Net	Acc	94.56	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	97.12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	94.84	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	92.62	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MIDAS	Accuracy	94.27	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	92.57	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	87.41	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa-Large + ICDA	Accuracy (%)	82.45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MIDAS	Accuarcy	85.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	General SLU Model w/ Profile	Accuracy	0.85	—	Unverified