ljw23/text_classification_tf

The purpose of this repository is to explore text classification methods in NLP with tensorflow

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., 2015)
• TextRNN (Liu et al., 2016)
• FastText (Joulin et al., 2016)
• VDCNN (Conneau 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., 2019)

Requirement

• Python 3
• Tensorflow 2.0+
• Numpy 1.14.3+

Usage

Training

python train.py conf/train.json

Detail configurations and explanations see Configuration.

The training info will be outputted in standard output and log.logger_file.

Evaluation

python eval.py conf/train.json

• if eval.is_flat = false, hierarchical evaluation will be outputted.
• eval.model_dir is the model to evaluate.
• data.test_json_files is the input text file to evaluate.

The evaluation info will be outputed in eval.dir.

Input Data Format

JSON example:

{
    "doc_label": ["Computer--MachineLearning--DeepLearning", "Neuro--ComputationalNeuro"],
    "doc_token": ["I", "love", "deep", "learning"],
    "doc_keyword": ["deep learning"],
    "doc_topic": ["AI", "Machine learning"]
}

"doc_keyword" and "doc_topic" are optional.

Performance

0. Dataset

Dataset	Taxonomy	#Label	#Training	#Test
RCV1	Tree	103	23,149	781,265
Yelp	DAG	539	87,375	37,265

• RCV1: Lewis et al., 2004
• Yelp: Yelp

1. Compare with state-of-the-art

Text Encoders	Micro-F1 on RCV1	Micro-F1 on Yelp
HR-DGCNN (Peng et al., 2018)	0.7610	-
HMCN (Wehrmann et al., 2018)	0.8080	0.6640
Ours	0.8313	0.6704

• HR-DGCNN: Peng et al., 2018
• HMCN: Wehrmann et al., 2018

Acknowledgement

Some public codes are referenced by our toolkit:

• https://github.com/ailias/Focal-Loss-implement-on-Tensorflow/
• https://github.com/brightmart/text_classification

Update

• 2019-04-29, init version