# An Entity-Driven Framework for Abstractive Summarization

arXiv: https://arxiv.org/abs/1909.02059 · HTML: https://mlsanity.com/paper/1909.02059/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand](https://mlsanity.com/paper/2112.04139/) (2021)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [Learning to Revise References for Faithful Summarization](https://mlsanity.com/paper/2204.10290/) (2022)
- [Controllable Summarization with Constrained Markov Decision Process](https://mlsanity.com/paper/2108.03405/) (2021)
- [NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist](https://mlsanity.com/paper/2305.08566/) (2023)
- [Leveraging Information Bottleneck for Scientific Document Summarization](https://mlsanity.com/paper/2110.01280/) (2021)
- [Major Entity Identification: A Generalizable Alternative to Coreference Resolution](https://mlsanity.com/paper/2406.14654/) (2024)
- [Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling](https://mlsanity.com/paper/2110.07198/) (2021)
- [AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction](https://mlsanity.com/paper/2310.20352/) (2023)
- [How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation](https://mlsanity.com/paper/2101.11298/) (2021)
- [Nutri-bullets: Summarizing Health Studies by Composing Segments](https://mlsanity.com/paper/2103.11921/) (2021)
- [SPEER: Sentence-Level Planning of Long Clinical Summaries via Embedded Entity Retrieval](https://mlsanity.com/paper/2401.02369/) (2024)
- [How to Find Strong Summary Coherence Measures? A Toolbox and a Comparative Study for Summary Coherence Measure Evaluation](https://mlsanity.com/paper/2209.06517/) (2022)
- [Nutribullets Hybrid: Multi-document Health Summarization](https://mlsanity.com/paper/2104.03465/) (2021)
- [Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature](https://mlsanity.com/paper/2203.15959/) (2022)
- [Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures](https://mlsanity.com/paper/2204.11190/) (2022)
- [A Condense-then-Select Strategy for Text Summarization](https://mlsanity.com/paper/2106.10468/) (2021)
- [Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning](https://mlsanity.com/paper/2302.02124/) (2023)
- [An entity-guided text summarization framework with relational heterogeneous graph neural network](https://mlsanity.com/paper/2302.03205/) (2023)
- [Scalable Detection of Salient Entities in News Articles](https://mlsanity.com/paper/2405.20461/) (2024)
- [Enhancing Long Document Long Form Summarisation with Self-Planning](https://mlsanity.com/paper/2512.17179/) (2025)
- [Augmented Abstractive Summarization With Document-LevelSemantic Graph](https://mlsanity.com/paper/2109.06046/) (2021)
- [Reinforced Abstractive Summarization with Adaptive Length Controlling](https://mlsanity.com/paper/2112.07534/) (2021)
- [Reinforcing Semantic-Symmetry for Document Summarization](https://mlsanity.com/paper/2112.07583/) (2021)
- [Topic-Aware Encoding for Extractive Summarization](https://mlsanity.com/paper/2112.09572/) (2021)

## Abstract (arXiv)

Abstractive summarization systems aim to produce more coherent and concise summaries than their extractive counterparts. Popular neural models have achieved impressive results for single-document summarization, yet their outputs are often incoherent and unfaithful to the input. In this paper, we introduce SENECA, a novel System for ENtity-drivEn Coherent Abstractive summarization framework that leverages entity information to generate informative and coherent abstracts. Our framework takes a two-step approach: (1) an entity-aware content selection module first identifies salient sentences from the input, then (2) an abstract generation module conducts cross-sentence information compression and abstraction to generate the final summary, which is trained with rewards to promote coherence, conciseness, and clarity. The two components are further connected using reinforcement learning. Automatic evaluation shows that our model significantly outperforms previous state-of-the-art on ROUGE and our proposed coherence measures on New York Times and CNN/Daily Mail datasets. Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.