RefSum: Refactoring Neural Summarization

By Yixin Liu, Zi-Yi Dou, Pengfei Liu. 2021

43 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Summarization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Pengfei Liu
2. Graham Neubig
3. Yixin Liu
4. Peng Liu
5. Weizhe Yuan
6. Jinlan Fu
7. Dragomir R. Radev
8. Ji-rong Wen

In Summarization

1. Yixin Liu
2. Pengfei Liu
3. Graham Neubig
4. Peng Liu
5. Weizhe Yuan
6. Dragomir R. Radev
7. Jinlan Fu
8. Mohit Bansal

Citations in the corpus

• ExplainaBoard: An Explainable Leaderboard for NLP (2021, methodology): “10 In practice, for NER task, we use the recently proposed S PAN N ER (Fu et al., 2021) as a combiner, and for text summarization we employed R EFACTOR , a state-of-the-art ensemble approach (Liu et al., 2021).”
• How well do you know your summarization datasets? (2021, unknown): “The past few years have witnessed major breakthroughs and improvements in automatic summarization (See et al., 2017; Celikyilmaz et al., 2018; Jadhav and Rajan, 2018; Liu and Lapata, 2019; Liu, 2019; Dou et al., 2020; Yuan et al., 2021; Liu et al., 2021).”
• SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization (2021, methodology): “Specifically, inspired by the recent work of Zhong et al. (2020); Liu et al. (2021b) on text summarization, we propose to use a two-stage model for abstractive summarization, where a Seq2Seq model is first trained to generate candidate summaries with MLE loss, and then a parameterized evaluation…”
• Pre-Trained Language Models for Text Generation: A Survey (2022, background): “Refactor [121] first generated multiple summaries under different setups and then scored them and finally selected an optimal candidate summary.”
• BRIO: Bringing Order to Abstractive Summarization (2022, methodology): “We calculate 8The calculation is performed using ExplainaBoard (Liu et al., 2021a). https://github.com/neulab/ExplainaBoard.”