You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: english/intent_detection_slot_filling.md
+4
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,8 @@ ATIS (Air Travel Information System) (Hemphill et al.) is a dataset by Microsoft
18
18
| Model | Slot F1 Score | Intent Accuracy | Paper / Source | Code |
19
19
| ------ | ------ | ------ | ------ | ------ |
20
20
| Bi-model with decoder | 96.89 | 98.99 |[A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling](https://arxiv.org/abs/1812.10235)|
21
+
| Stack-Propagation + BERT | 96.10 | 97.50 |[A Stack-Propagation Framework with Token-level Intent Detection for Spoken Language Understanding](https://arxiv.org/abs/1909.02188)|[Official](https://github.com/LeePleased/StackPropagation-SLU)|
22
+
| Stack-Propagation | 95.90 | 96.90 |[A Stack-Propagation Framework with Token-level Intent Detection for Spoken Language Understanding](https://arxiv.org/abs/1909.02188)|[Official](https://github.com/LeePleased/StackPropagation-SLU)|
21
23
| Attention Encoder-Decoder NN | 95.87 | 98.43 |[Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://arxiv.org/abs/1609.01454)|
22
24
| SF-ID (BLSTM) network | 95.80 | 97.76 |[A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling](https://arxiv.org/abs/1907.00390)|[Official](https://github.com/ZephyrChenzf/SF-ID-Network-For-NLU)|
23
25
| Capsule-NLU | 95.20 | 95.00 |[Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://arxiv.org/abs/1812.09471)|[Official](https://github.com/czhang99/Capsule-NLU)|
@@ -37,6 +39,8 @@ SNIPS is a dataset by Snips.ai for Intent Detection and Slot Filling benchmarkin
37
39
38
40
| Model | Slot F1 Score | Intent Accuracy | Paper / Source | Code |
39
41
| ------ | ------ | ------ | ------ | ------ |
42
+
| Stack-Propagation + BERT | 97.00 | 99.00 |[A Stack-Propagation Framework with Token-level Intent Detection for Spoken Language Understanding](https://arxiv.org/abs/1909.02188)|[Official](https://github.com/LeePleased/StackPropagation-SLU)|
43
+
| Stack-Propagation | 94.20 | 98.00 |[A Stack-Propagation Framework with Token-level Intent Detection for Spoken Language Understanding](https://arxiv.org/abs/1909.02188)|[Official](https://github.com/LeePleased/StackPropagation-SLU)|
40
44
| SF-ID (BLSTM) network | 92.23 | 97.43 |[A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling](https://arxiv.org/abs/1907.00390)|[Official](https://github.com/ZephyrChenzf/SF-ID-Network-For-NLU)|
41
45
| Capsule-NLU | 91.80 | 97.70 |[Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://arxiv.org/abs/1812.09471)|[Official](https://github.com/czhang99/Capsule-NLU)|
42
46
| Slot-Gated BLSTM with Attension | 88.80 | 97.00 |[Slot-Gated Modeling for Joint Slot Filling and Intent Prediction](https://www.csie.ntu.edu.tw/~yvchen/doc/NAACL18_SlotGated.pdf)|[Official](https://github.com/MiuLab/SlotGated-SLU)|
0 commit comments