Papers › SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling

SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling

26 Aug 2021arXiv:2108.11711archive 2025-07-28

Fengyu Cai, Wanhao Zhou, Fei Mi, Boi Faltings

Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems. Most existing approaches assume that only a single intent exists in an utterance. However, there are often multiple intents within an utterance in real-life scenarios. In this paper, we propose a multi-intent NLU framework, called SLIM, to jointly learn multi-intent detection and slot filling based on BERT. To fully exploit the existing annotation data and capture the interactions between slots and intents, SLIM introduces an explicit slot-intent classifier to learn the many-to-one mapping between slots and intents. Empirical results on three public multi-intent datasets demonstrate (1) the superior performance of SLIM compared to the current state-of-the-art for NLU with multiple intents and (2) the benefits obtained from the slot-intent classifier.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

TRUMANCFY/SLIM officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Intent Detection Natural Language Understanding Semantic Frame Parsing Slot Filling slot-filling

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Intent Detection	MixATIS	SLIM	Accuracy	78.3	#10 of 15	Archive leaderboard	report
Intent Detection	MixSNIPS	SLIM	Accuracy	97.2	#9 of 16	Archive leaderboard	report
Slot Filling	MixATIS	SLIM	Micro F1	88.5	#7 of 15	Archive leaderboard	report
Slot Filling	MixSNIPS	SLIM	Micro F1	96.5	#3 of 16	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections