Importance of Copying Mechanism for News Headline Generation
This addresses the problem of generating accurate headlines for news articles, especially in morphologically rich languages like Russian, by enabling models to copy named entities, though it is incremental as it builds on existing copying mechanisms.
The study tackled news headline generation by validating that models with a copying mechanism outperform those without, achieving a mean ROUGE score of 23, which is 8 points higher than a similar model without copying, and it performed better than any known model on a new Russian news dataset.
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.