Tag
This paper proposes a novel method for extractive text summarization using hypergraph domination, comparing its performance with existing graph-based approaches.
The paper introduces a hybrid hierarchical 1D-CNN-BiLSTM framework for extractive summarization of biomedical and clinical text, designed to preserve factuality by selecting sentences directly from source documents rather than generating new text.
LaMSUM is a novel multi-level framework using LLMs to generate extractive summaries of large collections of harassment incident reports from citizen reporting platforms. The approach outperforms state-of-the-art extractive summarization methods and addresses challenges like limited LLM context windows and code-mixed language processing.