Russian News Clustering and Headline Selection Shared Task

TL;DR

This paper introduces a shared task on Russian news clustering and headline selection, providing new datasets for event detection, headline selection, and generation, along with baseline approaches and analysis.

Contribution

It presents the first public Russian datasets for news event detection and headline selection, and a novel clustering-based dataset for headline generation.

Findings

First public Russian datasets for event detection and headline selection

Baseline approaches for clustering and headline tasks analyzed

Multiple reference headlines per cluster for generation dataset

Abstract

This paper presents the results of the Russian News Clustering and Headline Selection shared task. As a part of it, we propose the tasks of Russian news event detection, headline selection, and headline generation. These tasks are accompanied by datasets and baselines. The presented datasets for event detection and headline selection are the first public Russian datasets for their tasks. The headline generation dataset is based on clustering and provides multiple reference headlines for every cluster, unlike the previous datasets. Finally, the approaches proposed by the shared task participants are reported and analyzed.