Model: Text Summary Dev Guide

[WenheLI]

To develop a text summary model, three key plugins are required modelDefine, modelTrain, and modelEval.

• modelDefine: this plugin requires you to write the definition of a model (mainly network structure)
• modelTrain: this plugin is about how to feed data into the model and how to adjust the model weights
• modelEval: this plugin requires you to feed some test data and evaluate the output.

• Note: for this task, you might need to use some tokenize trick in NLP, you can put this process in either modelDefine or modelTrain.

As for the dataAccess and dataCollect, I think csv-data-collect & csv-data-access will help you out. The only thing for you is to find suitable dataset in this task. If the dataset is not in csv format, you might also need to write you own dataAccess & dataCollect.

We can use this thread as a plugin dev Q&A