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% relative in perplexity and 2.84 points in ROUGE.
Event participant modelling with neural networks
Ottokar Tilk | Vera Demberg | Asad Sayeed | Dietrich Klakow | Stefan Thater
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing