Automatic Generation of Factual News Headlines in Finnish
This addresses the need for automated headline generation in Finnish news production, though it is incremental as it adapts existing methods to a new language.
The researchers tackled the problem of generating factual news headlines in Finnish by modeling it as a summarization task, where a model produces concise headlines from news articles, and the results demonstrated usability as a headline suggestion tool based on evaluation by expert journalists.
We present a novel approach to generating news headlines in Finnish for a given news story. We model this as a summarization task where a model is given a news article, and its task is to produce a concise headline describing the main topic of the article. Because there are no openly available GPT-2 models for Finnish, we will first build such a model using several corpora. The model is then fine-tuned for the headline generation task using a massive news corpus. The system is evaluated by 3 expert journalists working in a Finnish media house. The results showcase the usability of the presented approach as a headline suggestion tool to facilitate the news production process.