On Tracking Dialogue State by Inheriting Slot Values in Mentioned Slot Pools
Authors: Zhoujian Sun, Zhengxing Huang, Nai Ding
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conducted experiments on three annotated DST datasets, i.e., Multi WOZ 2.1, Multi WOZ 2.2, and WOZ 2.0, respectively [Eric et al., 2020; Zang et al., 2020; Wen et al., 2017]. Experimental results showed our model reached state of the art DST performance on Multi WOZ datasets. |
| Researcher Affiliation | Collaboration | 1Zhejiang Lab 2Zhejiang University sunzj@zhejianglab.edu.cn, {zhengxinghuang, nai ding}@zju.edu.cn |
| Pseudocode | No | The paper describes the model's structure and operations using text and mathematical equations, but it does not include explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | Yes | We released the source code of this paper at https://github.com/ZJLAB-AMMI/msp. |
| Open Datasets | Yes | We conducted experiments on three annotated DST datasets, i.e., Multi WOZ 2.1, Multi WOZ 2.2, and WOZ 2.0, respectively [Eric et al., 2020; Zang et al., 2020; Wen et al., 2017]. |
| Dataset Splits | Yes | Early stopping was employed based on the JGA of the development set. |
| Hardware Specification | No | The paper describes the architecture and parameter count of the BERT models used but does not specify the type of GPUs, CPUs, or other hardware on which the experiments were run. |
| Software Dependencies | No | The paper mentions using BERT, Adam optimizer, and Word Piece embeddings but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | The maximum input sequence length was set to 512 tokens after tokenization. The weights α, β, and γ were 0.6, 0.2, and 0.2, respectively. The initial learning rate was set to 1e 5, and the total epoch number was set to 20. We conducted training with a warmup proportion of 10% and let the learning rate decay linearly after the warmup phase. Early stopping was employed based on the JGA of the development set. |