Discovering New Intents with Deep Aligned Clustering
Authors: Hanlei Zhang, Hua Xu, Ting-En Lin, Rui Lyu14365-14373
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods. |
| Researcher Affiliation | Collaboration | Hanlei Zhang,1, 2 Hua Xu,1, 2 Ting-En Lin1, 2, Rui Lyu1, 3 1State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China, 2 Beijing National Research Center for Information Science and Technology (BNRist), Beijing 100084, China 3 Beijing University of Posts and Telecommunications University, Beijing 100876, China zhang-hl20@mails.tsinghua.edu.cn, xuhua@tsinghua.edu.cn, ting-en.lte@alibaba-inc.com, lvrui2017@bupt.edu.cn |
| Pseudocode | No | The paper describes the method and architecture through text and diagrams but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The codes are released at https://github.com/thuiar/Deep Aligned Clustering. |
| Open Datasets | Yes | CLINC It is an intent classification dataset (Larson et al. 2019)... BANKING It is a fine-grained dataset in the banking domain (Casanueva et al. 2020)... |
| Dataset Splits | Yes | Dataset #Classes (Known + Unknown) #Training #Validation #Test Vocabulary Length (max / mean) CLINC 150 (113 + 37) 18,000 2,250 2,250 7,283 28 / 8.31 BANKING 77 (58 + 19) 9,003 1,000 3,080 5,028 79 / 11.91 |
| Hardware Specification | No | The paper does not provide specific hardware details (like GPU models, CPU types, or memory amounts) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'Py Torch' but does not specify a version number for it or other software dependencies. |
| Experiment Setup | Yes | The training batch size is 128, the learning rate is 5e 5, and the dimension of intent features D is 768. Moreover, as suggested in (Lin, Xu, and Zhang 2020), we freeze all but the last transformer layer parameters to speed up the training procedure and improve the training efficiency with the backbone of BERT. |