# PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream

arXiv: https://arxiv.org/abs/2302.05550 · HTML: https://mlsanity.com/paper/2302.05550/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 59 references that are in the map.
- First posted on arXiv 10 Feb 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Heterogeneous Graph Neural Networks for Extractive Document Summarization](https://mlsanity.com/paper/2004.12393/) (2020)
- [A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal](https://mlsanity.com/paper/2005.10070/) (2020)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization](https://mlsanity.com/paper/2110.08499/) (2021)
- [Text Summarization Techniques: A Brief Survey](https://mlsanity.com/paper/1707.02268/) (2017)
- [Multi-document Summarization via Deep Learning Techniques: A Survey](https://mlsanity.com/paper/2011.04843/) (2020)
- [Exploring Neural Models for Query-Focused Summarization](https://mlsanity.com/paper/2112.07637/) (2021)
- [A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives](https://mlsanity.com/paper/2102.12982/) (2021)
- [Generating Representative Headlines for News Stories](https://mlsanity.com/paper/2001.09386/) (2020)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning](https://mlsanity.com/paper/2010.00117/) (2020)
- [Examining the State-of-the-Art in News Timeline Summarization](https://mlsanity.com/paper/2005.10107/) (2020)
- [Generating Query Focused Summaries from Query-Free Resources](https://mlsanity.com/paper/2012.14774/) (2020)
- [SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression](https://mlsanity.com/paper/2007.08954/) (2020)
- [BASS: Boosting Abstractive Summarization with Unified Semantic Graph](https://mlsanity.com/paper/2105.12041/) (2021)
- [Controllable Summarization with Constrained Markov Decision Process](https://mlsanity.com/paper/2108.03405/) (2021)
- [UCPhrase: Unsupervised Context-aware Quality Phrase Tagging](https://mlsanity.com/paper/2105.14078/) (2021)
- [Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream](https://mlsanity.com/paper/2206.04792/) (2022)
- [Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization](https://mlsanity.com/paper/1708.07690/) (2017)

## Built on by (most cited first, 7 of 7)

- [Online Drift Detection with Maximum Concept Discrepancy](https://mlsanity.com/paper/2407.05375/) (2024)
- [Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization](https://mlsanity.com/paper/2305.01951/) (2023)
- [Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding](https://mlsanity.com/paper/2304.04099/) (2023)
- [MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities](https://mlsanity.com/paper/2304.01969/) (2023)
- [Incremental Extractive Opinion Summarization Using Cover Trees](https://mlsanity.com/paper/2401.08047/) (2024)
- [CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory](https://mlsanity.com/paper/2601.02708/) (2026)
- [Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams](https://mlsanity.com/paper/2603.19250/) (2026)

## Abstract (arXiv)

Summarizing text-rich documents has been long studied in the literature, but most of the existing efforts have been made to summarize a static and predefined multi-document set. With the rapid development of online platforms for generating and distributing text-rich documents, there arises an urgent need for continuously summarizing dynamically evolving multi-document sets where the composition of documents and sets is changing over time. This is especially challenging as the summarization should be not only effective in incorporating relevant, novel, and distinctive information from each concurrent multi-document set, but also efficient in serving online applications. In this work, we propose a new summarization problem, Evolving Multi-Document sets stream Summarization (EMDS), and introduce a novel unsupervised algorithm PDSum with the idea of prototype-driven continuous summarization. PDSum builds a lightweight prototype of each multi-document set and exploits it to adapt to new documents while preserving accumulated knowledge from previous documents. To update new summaries, the most representative sentences for each multi-document set are extracted by measuring their similarities to the prototypes. A thorough evaluation with real multi-document sets streams demonstrates that PDSum outperforms state-of-the-art unsupervised multi-document summarization algorithms in EMDS in terms of relevance, novelty, and distinctiveness and is also robust to various evaluation settings.