# Abstractive Multi-Document Summarization via Phrase Selection and Merging

arXiv: https://arxiv.org/abs/1506.01597 · HTML: https://mlsanity.com/paper/1506.01597/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2015.

## Built on by (most cited first, 10 of 10)

- [Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization](https://mlsanity.com/paper/2305.13091/) (2023)
- [Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration](https://mlsanity.com/paper/2109.06304/) (2021)
- [UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining](https://mlsanity.com/paper/2202.13469/) (2022)
- [Proposition-Level Clustering for Multi-Document Summarization](https://mlsanity.com/paper/2112.08770/) (2021)
- [Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications](https://mlsanity.com/paper/2409.18454/) (2024)
- [iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration](https://mlsanity.com/paper/2109.11621/) (2021)
- [TWAG: A Topic-Guided Wikipedia Abstract Generator](https://mlsanity.com/paper/2106.15135/) (2021)
- [Modeling Endorsement for Multi-Document Abstractive Summarization](https://mlsanity.com/paper/2110.07844/) (2021)
- [A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2305.08503/) (2023)
- [Controllable Multi-document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards](https://mlsanity.com/paper/2310.03473/) (2023)

## Abstract (arXiv)

We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases. Different from existing abstraction-based approaches, our method first constructs a pool of concepts and facts represented by phrases from the input documents. Then new sentences are generated by selecting and merging informative phrases to maximize the salience of phrases and meanwhile satisfy the sentence construction constraints. We employ integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary. Experimental results on the benchmark data set TAC 2011 show that our framework outperforms the state-of-the-art models under automated pyramid evaluation metric, and achieves reasonably well results on manual linguistic quality evaluation.