Papers › Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot...

Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence

1 Dec 2022Conference on Empirical Methods in Natural Language Processing 2022 12archive 2025-07-28

Mengxiao Song, Bowen Yu, Li Quangang, Wang Yubin, Tingwen Liu, Hongbo Xu

Multi-intent detection and slot filling joint model attracts more and more attention since it can handle multi-intent utterances, which is closer to complex real-world scenarios. Most existing joint models rely entirely on the training procedure to obtain the implicit correlation between intents and slots. However, they ignore the fact that leveraging the rich global knowledge in the corpus can determine the intuitive and explicit correlation between intents and slots. In this paper, we aim to make full use of the statistical co-occurrence frequency between intents and slots as prior knowledge to enhance joint multiple intent detection and slot filling. To be specific, an intent-slot co-occurrence graph is constructed based on the entire training corpus to globally discover correlation between intents and slots. Based on the global intent-slot co-occurrence, we propose a novel graph neural network to model the interaction between the two subtasks. Experimental results on two public multi-intent datasets demonstrate that our approach outperforms the state-of-the-art models.

PaperPDFCode

Code

smxiao/GISCo mentioned 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

Graph Neural NetworkIntent DetectionSemantic Frame ParsingSlot Fillingslot-filling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Intent Detection MixATIS Global Intent-Slot Co-occurence Accuracy 75.0 #14 of 15 Archive leaderboard report
Intent Detection MixSNIPS Global Intent-Slot Co-occurence Accuracy 95.5 #16 of 16 Archive leaderboard report
Slot Filling MixATIS Global Intent-Slot Co-occurence Micro F1 88.5 #8 of 15 Archive leaderboard report
Slot Filling MixSNIPS Global Intent-Slot Co-occurence Micro F1 95.0 #12 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.

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