RankSum An unsupervised extractive text summarization based on rank fusion

TL;DR

The paper introduces Ranksum, an unsupervised extractive summarization method that fuses multiple sentence features using learned weights, achieving superior results on benchmark datasets.

Contribution

It presents a novel unsupervised rank fusion approach combining topic, semantic, keyword, and positional features for extractive summarization.

Findings

Outperforms state-of-the-art methods on CNN/DailyMail and DUC 2002 datasets.

Effectively combines multiple features through learned weight fusion.

Demonstrates generalization of fusion weights across datasets.

Abstract

In this paper, we propose Ranksum, an approach for extractive text summarization of single documents based on the rank fusion of four multi-dimensional sentence features extracted for each sentence: topic information, semantic content, significant keywords, and position. The Ranksum obtains the sentence saliency rankings corresponding to each feature in an unsupervised way followed by the weighted fusion of the four scores to rank the sentences according to their significance. The scores are generated in completely unsupervised way, and a labeled document set is required to learn the fusion weights. Since we found that the fusion weights can generalize to other datasets, we consider the Ranksum as an unsupervised approach. To determine topic rank, we employ probabilistic topic models whereas semantic information is captured using sentence embeddings. To derive rankings using sentence embeddings, we utilize Siamese networks to produce abstractive sentence representation and then we formulate a novel strategy to arrange them in their order of importance. A graph-based strategy is applied to find the significant keywords and related sentence rankings in the document. We also formulate a sentence novelty measure based on bigrams, trigrams, and sentence embeddings to eliminate redundant sentences from the summary. The ranks of all the sentences computed for each feature are finally fused to get the final score for each sentence in the document. We evaluate our approach on publicly available summarization datasets CNN/DailyMail and DUC 2002. Experimental results show that our approach outperforms other existing state-of-the-art summarization methods.