Allen Institute for AI
Part 1: Quick Start

Training and prediction

This chapter will outline how to train your model and run prediction on new data

In the previous chapter, we learned how to write your own dataset reader and model. In this chapter, we are going to train the text classification model and make predictions for new inputs. At this point, there are two ways to proceed: you can write your own script to construct the dataset reader and model and run the training loop, or you can write a configuration file and use the allennlp train command. We will show you how to use both ways here.

1Training the model with your own script

2Training the model with allennlp train

3Evaluating the model

4Making predictions for unlabeled inputs