NeuralNLP-NeuralClassifier

Tencent/NeuralNLP-NeuralClassifier is ranked 9,245 among these 8 peers; Yvictor/TradingGym is ranked 9,244.

NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit Introduction NeuralClassifier is designed for quick implementation of neural models for hierarchical multi-label classification task, which is more challenging and common in real-world scenarios. A salient feature is that NeuralClassifier currently provides a variety of text encoders, such as FastText, TextCNN, TextRNN, RCNN, VDCNN, DPCNN, DRNN, AttentiveConvNet and Transformer encoder, etc. It also supports other text classification scenarios, including binary-class and multi-class classification. Experiments show

that models built in our toolkit achieve comparable performance with reported results in the literature. Support tasks Binary-class text classifcation Multi-class text classification Multi-label text classification Hiearchical (multi-label) text classification (HMC) Support text encoders TextCNN (Kim, 2014) RCNN (Lai et al. , 2016) DPCNN (Johnson and Zhang, 2017) AttentiveConvNet (Yin and Schutze, 2017) DRNN (Wang, 2018) Region embedding (Qiao et al. , 2018) Transformer encoder (Vaswani et al. , 2017) Star-Transformer encoder (Guo et al. 3+ System Architecture

Usage Training How to train a non-hierarchical classifier set task_info. How to train a hierarchical classifier using hierarchial penalty set task_info. model_name can be How to train a hierarchical classifier with HMCN set task_info. set model_name = ***Detail configurations and explanations see Configuration. *** The training info will be outputted in standard output and log. is\_flat = false, hierarchical evaluation will be outputted. test\_json\_files is the input text file to evaluate. The evaluation info

will be outputed in eval. top\_k is the number of labels to output. The predict info will be outputed in predict. Dataset Dataset Taxonomy #Label #Training #Test RCV1 Tree 103 23,149 781,265 Yelp DAG 539 87,375 37,265 RCV1: Lewis et al. Compare with state-of-the-art Text Encoders Micro-F1 on RCV1 Micro-F1 on Yelp HR-DGCNN (Peng et al. Different text encoders Text Encoders RCV1 Yelp Micro-F1 Macro-F1 Micro-F1

Macro-F1 TextCNN 0. 3895 performance got with 300d pretrained glove embedding 3. Hierarchical vs Flat Text Encoders Hierarchical Flat Micro-F1 Macro-F1 Micro-F1 Macro-F1 TextCNN 0. 4745 Acknowledgement Some public codes are referenced by our toolkit: Update 2019-04-29, init version