Low-Resource Neural Headline Generation
share
Recent neural headline generation models have shown great results, but are generally trained on very large datasets. We focus our efforts on improving headline quality on smaller datasets by the means of pretraining. We propose new methods that enable pre-training all the parameters of the model and utilize all available text, resulting in improvements by up to 32.4 in perplexity and 2.84 points in ROUGE.
READ FULL TEXT