Importance of Copying Mechanism for News Headline Generation

TL;DR

This paper demonstrates that incorporating a copying mechanism in news headline generation models significantly improves performance, especially in morphologically rich languages like Russian, by effectively handling new named entities.

Contribution

It validates that models with copying mechanisms outperform those without, achieving higher ROUGE scores and better results on Russian news datasets.

Findings

Copying mechanism improves ROUGE scores by 8 points.

Model outperforms existing models on Russian news datasets.

Copying mechanism effectively handles new named entities.

Abstract

News headline generation is an essential problem of text summarization because it is constrained, well-defined, and is still hard to solve. Models with a limited vocabulary can not solve it well, as new named entities can appear regularly in the news and these entities often should be in the headline. News articles in morphologically rich languages such as Russian require model modifications due to a large number of possible word forms. This study aims to validate that models with a possibility of copying words from the original article performs better than models without such an option. The proposed model achieves a mean ROUGE score of 23 on the provided test dataset, which is 8 points greater than the result of a similar model without a copying mechanism. Moreover, the resulting model performs better than any known model on the new dataset of Russian news.