MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes

We introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at each step with information on the current extraction history. When MemSum iteratively selects sentences into the summary, it considers a broad information set that would intuitively also be used by humans in this task: 1) the text content of the sentence, 2) the global text context of the rest of the document, and 3) the extraction history consisting of the set of sentences that have already been extracted. With a lightweight architecture, MemSum obtains state-of-the-art test-set performance (ROUGE) in summarizing long documents taken from PubMed, arXiv, and GovReport. Ablation studies demonstrate the importance of local, global, and history information. A human evaluation confirms the high quality and low redundancy of the generated summaries, stemming from MemSum's awareness of extraction history.

PDF Abstract ACL 2022 PDF ACL 2022 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Summarization Arxiv HEP-TH citation graph MemSum (extractive) ROUGE-1 48.42 # 8
ROUGE-2 20.30 # 8
ROUGE-L 42.54 # 8
Extractive Text Summarization GovReport MemSum (extractive) Avg. Test Rouge1 59.43 # 1
Avg. Test Rouge2 28.60 # 1
Avg. Test RougeLsum 56.69 # 1
Text Summarization Pubmed MemSum (extractive) ROUGE-1 49.25 # 6
ROUGE-2 22.94 # 6
ROUGE-L 44.42 # 5


No methods listed for this paper. Add relevant methods here