Towards Joint Intent Detection and Slot Filling via Higher-order Attention
Authors: Dongsheng Chen, Zhiqi Huang, Xian Wu, Shen Ge, Yuexian Zou
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results show that our approach outperforms the state-of-the-art results. We also conduct experiments on the new SLURP dataset, and give a discussion on HAN s properties, i.e., robustness and generalization. Extensive experiments on two benchmark datasets SNIPS [Coucke et al., 2018] and ATIS [Hemphill et al., 1990] proves the advancement of our approach. We also conduct a set of ablation studies to justify the importance of key components in our designed architecture. |
| Researcher Affiliation | Collaboration | 1School of ECE, Peking University, China 2Tencent Medical AI Lab, China |
| Pseudocode | No | The paper provides mathematical equations and descriptions of the architecture but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper provides a link to the SLURP dataset (https://github.com/pswietojanski/slurp/tree/master/dataset/slurp) but does not provide a link or statement for the open-source code of their proposed methodology. |
| Open Datasets | Yes | We conduct major experiments on SNIPS and ATIS. SNIPS has 13,084 utterances for training, 700 for validation, and 700 for testing. ATIS has 4,478 utterances for training, 500 for validation, and 893 for testing. Both datasets follow the partition as in [Goo et al., 2018]. We also conduct additional experiments on the recently released dataset SLURP1. 1https://github.com/pswietojanski/slurp/tree/master/dataset/slurp |
| Dataset Splits | Yes | SNIPS has 13,084 utterances for training, 700 for validation, and 700 for testing. ATIS has 4,478 utterances for training, 500 for validation, and 893 for testing. |
| Hardware Specification | Yes | All experiments in this paper were conducted on a single NVIDIA Ge Force GTX 2080 Ti GPU, and the model was implemented in Py Torch. |
| Software Dependencies | No | The paper mentions that "the model was implemented in Py Torch" but does not specify a version number for PyTorch or any other software dependencies. |
| Experiment Setup | Yes | We use Adam as the optimizer. The size of hidden vector d is set to 128, batch size is 32, and learning rate is 1e-3. |