Data Augmentation for Abstractive Query-Focused Multi-Document Summarization

By Ramakanth Pasunuru, Asli Celikyilmaz, Michel Galley, Chenyan Xiong, Yizhe Zhang, Mohit Bansal, Jianfeng Gao. 2021

46 citations recorded by the source corpus.

The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets. We present two QMDS training datasets, which we construct using two data augmentation methods: (1) transferring the commonly used single-document CNN/Daily Mail summarization dataset to create the QMDSCNN dataset, and (2) mining search-query logs to create the QMDSIR dataset. These two datasets have complementary properties, i.e., QMDSCNN has real summaries but queries are simulated, while QMDSIR has real queries but simulated summaries. To cover both these real summary and query aspects, we build abstractive end-to-end neural network models on the combined datasets that yield new state-of-the-art transfer results on DUC datasets. We also introduce new hierarchical encoders that enable a more efficient encoding of the query together with multiple documents. Empirical results demonstrate that our data augmentation and encoding methods outperform baseline models on automatic metrics, as well as on human evaluations along multiple attributes.

Subfields: Artificial Intelligence, Management Science and Operations Research, Natural Language Processing, 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. Ji-rong Wen
2. Wayne Xin Zhao
3. Jian-Yun Nie
4. Quan Z. Sheng
5. Hu Wang
6. Tianyi Tang
7. Junyi Li
8. Mingyu Guo

In Management Science and Operations Research

1. Jian-Yun Nie
2. Ji-rong Wen
3. Quan Z. Sheng
4. Wayne Xin Zhao
5. W. Zhang

In Natural Language Processing

1. Jian-Yun Nie
2. Ji-rong Wen
3. Quan Z. Sheng
4. Hu Wang
5. Tianyi Tang
6. Junyi Li
7. Mingyu Guo
8. Congbo Ma

Citations in the corpus

• Multi-document Summarization via Deep Learning Techniques: A Survey (2020, background): “It tries to solve realistic query-oriented scenario problems and only summarizes important information that best answers the query in a logical order [125].”
• Pre-Trained Language Models for Text Generation: A Survey (2022, methodology): “One line of research is to use retrieval models to obtain real data from external corpora as the augmented data [142, 193].”