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

07/19/2021
by   Nianlong Gu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/18/2022

GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state

Handling long texts with structural information and excluding redundancy...
research
11/06/2018

DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization

We propose DeepChannel, a robust, data-efficient, and interpretable neur...
research
06/19/2021

A Condense-then-Select Strategy for Text Summarization

Select-then-compress is a popular hybrid, framework for text summarizati...
research
10/03/2021

Multi-Document Keyphrase Extraction: A Literature Review and the First Dataset

Keyphrase extraction has been comprehensively researched within the sing...
research
05/04/2020

Noise Pollution in Hospital Readmission Prediction: Long Document Classification with Reinforcement Learning

This paper presents a reinforcement learning approach to extract noise i...
research
04/25/2018

Hierarchical RNN for Information Extraction from Lawsuit Documents

Every lawsuit document contains the information about the party's claim,...
research
08/01/2019

Mapping the uncertainty of 19th century West African slave origins using a Markov decision process model

The advent of modern computers has added an increased emphasis on channe...

Please sign up or login with your details

Forgot password? Click here to reset