Update Summarization Based on Co-Ranking with Constraints

Update summarization is an emerging summarization task of creating a short summary of a set of news articles, under the assumption that the user has already read a given set of earlier articles. In this paper, we propose a new co-ranking method to address the update summarization task. The proposed method integrates two co-ranking processes by adding strict constraints. In comparison with the original co-ranking method, the proposed method can compute more accurate scores of sentences for the purpose of update summarization. Evaluation results on the most recent TAC2011 dataset demonstrate that our proposed method can outperform the original co-ranking method and other baselines.