Papers › A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language...

A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding

5 Sep 2019IJCNLP 2019 11arXiv:1909.02188archive 2025-07-28

Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu

Intent detection and slot filling are two main tasks for building a spoken language understanding (SLU) system. The two tasks are closely tied and the slots often highly depend on the intent. In this paper, we propose a novel framework for SLU to better incorporate the intent information, which further guides the slot filling. In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge. In addition, to further alleviate the error propagation, we perform the token-level intent detection for the Stack-Propagation framework. Experiments on two publicly datasets show that our model achieves the state-of-the-art performance and outperforms other previous methods by a large margin. Finally, we use the Bidirectional Encoder Representation from Transformer (BERT) model in our framework, which further boost our performance in SLU task.

PaperPDFConference PDFCode

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

Code

LeePleased/StackPropagation-SLU officialmentioned in paperpytorch 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 DetectionSlot FillingSpoken Language Understandingslot-filling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Intent Detection ATIS Stack-Propagation (+BERT) Accuracy 97.50 #9 of 16 Archive leaderboard report
Intent Detection SNIPS Stack-Propagation (+BERT) Accuracy 99.0 #2 of 10 Archive leaderboard report
Intent Detection SNIPS Stack-Propagation Accuracy 98.00 #5 of 10 Archive leaderboard report
Slot Filling ATIS Stack-Propagation (+BERT) F1 0.9610 #5 of 14 Archive leaderboard report
Slot Filling SNIPS Stack-Propagation (+BERT) F1 97.00 #3 of 10 Archive leaderboard report
Slot Filling SNIPS Stack-Propagation F1 94.20 #5 of 10 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

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