Correlation-Guided Representation for Multi-Label Text Classification

Authors: Qian-Wen Zhang, Ximing Zhang, Zhao Yan, Ruifang Liu, Yunbo Cao, Min-Ling Zhang

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments over benchmark multi-label datasets clearly validate the effectiveness of the proposed approach, and further analysis demonstrates that it is competitive in both predicting lowfrequency labels and convergence speed. In this section, the datasets, comparing algorithms, evaluation metrics and parameter settings are introduced. We use two datasets for MLTC: AAPD [Yang et al., 2018] and RCV1-V2 [Lewis et al., 2004]. Table 1 summarizes the detailed characteristics of the two datasets. Each dataset is divided into a training set, a validation set, and a test set, which are used as basic divisions in the performance experiments of each algorithm [Yang et al., 2018]. We report the detailed experimental results of all comparing algorithms on two datasets in Table 2.
Researcher Affiliation Collaboration Qian-Wen Zhang1 , Ximing Zhang2 , Zhao Yan1 , Ruifang Liu2 , Yunbo Cao1 and Min-Ling Zhang3,4 1Tencent Cloud Xiaowei, Beijing 100080, China 2Beijing University of Posts and Telecommunications, Beijing 100876, China 3School of Computer Science and Engineering, Southeast University, Nanjing 210096, China 4Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China cowenzhang@tencent.com, ximingzhang@bupt.edu.cn, zhaoyan@tencent.com, lrf@bupt.edu.cn, yunbocao@tencent.com, zhangml@seu.edu.cn
Pseudocode No The paper describes its method using formulas and descriptive text but does not include a clearly labeled pseudocode or algorithm block.
Open Source Code No The paper does not contain any explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes We use two datasets for MLTC: AAPD [Yang et al., 2018] and RCV1-V2 [Lewis et al., 2004]. Table 1 summarizes the detailed characteristics of the two datasets. Each dataset is divided into a training set, a validation set, and a test set, which are used as basic divisions in the performance experiments of each algorithm [Yang et al., 2018].
Dataset Splits Yes Each dataset is divided into a training set, a validation set, and a test set, which are used as basic divisions in the performance experiments of each algorithm [Yang et al., 2018].
Hardware Specification Yes We implement our experiments in Tensorflow on NVIDIA Tesla P40.
Software Dependencies No The paper mentions "Tensorflow" and "base-uncased versions of BERT" but does not provide specific version numbers for these software dependencies, which are required for reproducibility.
Experiment Setup Yes The batch size is 32, the learning rate is 5e 5, and the window size of additional layer is 10. Based on WCard(S) and L(S) in Table 1, the maximum total input sequence length is 320. In addition, learning rate decay is added to the BERT training part, which starts with a large learning rate and then decays multiple times [Clark et al., 2019]. Note that all BERT-based models in this paper use learning rate decay technique to improve performance.