Papers › Transformer-Capsule Model for Intent Detection

Transformer-Capsule Model for Intent Detection

7 Feb 2020Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 2archive 2025-07-28

Aleksander Obuchowski, Michał Lew

Intent recognition is one of the most crucial tasks in NLUsystems, which are nowadays especially important for design-ing intelligent conversation. We propose a novel approach to intent recognition which involves combining transformer architecture with capsule networks. Our results show that such architecture performs better than original capsule-NLU net-work implementations and achieves state-of-the-art results on datasets such as ATIS, AskUbuntu , and WebApp.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Intent Detection Intent Recognition model

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Intent Detection	ATIS	Transformer-Capsule	Accuracy	98.89	#2 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

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer ReLU Residual Connection Softmax Transformer

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