CLApr 15, 2021

RefSum: Refactoring Neural Summarization

arXiv:2104.07210v1733 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the challenge of improving summarization performance for researchers by providing an off-the-shelf tool, though it is incremental as it builds on existing reranking and stacking techniques.

The paper tackles the problem of combining multiple text summarization systems by introducing a new framework called Refactor, which achieves a new state-of-the-art ROUGE-1 score of 46.18 on the CNN/DailyMail dataset.

Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or stacking to approach this problem. In this work, we highlight several limitations of previous methods, which motivates us to present a new framework Refactor that provides a unified view of text summarization and summaries combination. Experimentally, we perform a comprehensive evaluation that involves twenty-two base systems, four datasets, and three different application scenarios. Besides new state-of-the-art results on CNN/DailyMail dataset (46.18 ROUGE-1), we also elaborate on how our proposed method addresses the limitations of the traditional methods and the effectiveness of the Refactor model sheds light on insight for performance improvement. Our system can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements. We open-source all the code and provide a convenient interface to use it: https://github.com/yixinL7/Refactoring-Summarization. We have also made the demo of this work available at: http://explainaboard.nlpedia.ai/leaderboard/task-summ/index.php.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes