A Divide-and-Conquer Approach to the Summarization of Academic Articles

By Alexios Gidiotis, Grigorios Tsoumakas. 2020

18 citations recorded by the source corpus.

We present a novel divide-and-conquer method for the summarization of long documents. Our method processes the input in parts and generates a corresponding summary. These partial summaries are then combined in order to produce a final complete summary. Splitting the problem of long document summarization into smaller and simpler problems, reduces the computational complexity of the summarization process and leads to more training examples that at the same time contain less noise in the target summaries compared to the standard approach of producing the whole summary at once. Using a fairly simple sequence to sequence architecture with a combination of LSTM units and Rotational Units of Memory (RUM) our approach leads to state-of-the-art results in two publicly available datasets of academic articles.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On Generating Extended Summaries of Long Documents (2020, background): “Gidiotis, Stefanidis, and Tsoumakas (2020) proposed to use a divide and conquer (DANCER) approach (Gidiotis and Tsoumakas 2020) to identify the key sections of the paper to be summarized.”
Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm (2020, background): “The authors propose an extractive summarization method that utilizes DANCER, a divide and conquer approach for long document summarization.”