# In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes

arXiv: https://arxiv.org/abs/1909.10852 · HTML: https://mlsanity.com/paper/1909.10852/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Subjective Bias in Abstractive Summarization](https://mlsanity.com/paper/2106.10084/) (2021)
- [LeCoPCR: Legal Concept-guided Prior Case Retrieval for European Court of Human Rights cases](https://mlsanity.com/paper/2501.14114/) (2025)
- [Diverse Multi-Answer Retrieval with Determinantal Point Processes](https://mlsanity.com/paper/2211.16029/) (2022)
- [Exploiting Representation Bias for Data Distillation in Abstractive Text Summarization](https://mlsanity.com/paper/2312.06022/) (2023)

## Abstract (arXiv)

Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution. We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinantal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity. Without breaking the end to end architecture, DivCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines. All the reproducible codes and datasets are available online.