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

Open access
Date
2021-07Type
- Working Paper
ETH Bibliography
yes
Altmetrics
Abstract
We introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at any given time step with information on the current extraction history. Similar to previous models in this vein, MemSum iteratively selects sentences into the summary. Our innovation is in considering a broader information set when summarizing 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 nonetheless obtains state-of-the-art test-set performance (ROUGE score) on long document datasets (PubMed, arXiv, and GovReport). Supporting analysis demonstrates that the added awareness of extraction history gives MemSum robustness against redundancy in the source document. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000504034Publication status
publishedExternal links
Journal / series
Center for Law & Economics Working Paper SeriesVolume
Pages / Article No.
Publisher
Center for Law & Economics, ETH ZurichSubject
Automatic text summarization; Text summarization methods; Markov decision processesOrganisational unit
09627 - Ash, Elliott / Ash, Elliott
Related publications and datasets
Is identical to: http://hdl.handle.net/20.500.11850/529326
More
Show all metadata
ETH Bibliography
yes
Altmetrics