Single-Document Summarization Using Sentence Embeddings and K-Means Clustering

This paper proposes a novel method for extractive single document summarization using K-Means clustering and Sentence Embeddings. Sentence embeddings were processed by K-Means algorithm into a number of clusters depending on the required summary size. Sentences in a given cluster contained similar information, and the most appropriate sentence was picked and included in the summary for each cluster by a ridge regression sentence scoring model. Experimental ROUGE score evaluation of summaries of various lengths for the DUC 2001 dataset demonstrated the effectiveness of the approach.