Graph-based Ranking Algorithms for Sentence Extraction, Applied to Text Summarization

By Rada Mihalcea. Annual Meeting of the Association for Computational Linguistics, 2004

525 citations recorded by the source corpus.

This paper presents an innovative unsupervised method for automatic sentence extraction using graph-based ranking algorithms. We evaluate the method in the context of a text summarization task, and show that the results obtained compare favorably with previously published results on established benchmarks.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/2aeb08c93d6db8f305c015e593f753e2115a8750

How researchers see this paper

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

In Artificial Intelligence

1. J. Bilmes
2. Hui-Ching Lin
3. Ani Nenkova
4. Ido Dagan
5. Baotian Hu
6. Paul Tarau
7. Qingcai Chen
8. Marina Litvak

Citations in the corpus

• How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature (2019, background): “TextRank Sentences are scored by their centrality in the graph with sentences as the nodes (Erkan and Radev, 2004; Mihalcea, 2004).”
• Multi-document Summarization via Budgeted Maximization of Submodular Functions (2010, methodology): “from automatic keyphrase extraction and word sense disambiguation, to extractive summarization (Mihalcea et al., 2004; Mihalcea, 2004).”
• Variations of the Similarity Function of TextRank for Automated Summarization (2016, background): “It is domain and language independent since it does not require deep linguistic knowledge, nor domain or language specific annotated corpora [16].”
• Graph-Based Keyword Extraction for Single-Document Summarization (2008, background): “A similar idea can be applied to lexical or semantic graphs extracted from text documents, in order to extract the most significant blocks (words, phrases, sentences, etc.) for the summary (Mi-halcea and Tarau, 2004; Mihalcea, 2004).”
• LCSTS: A Large Scale Chinese Short Text Summarization Dataset (2015, background): “some researches focused on the unsupervised methods [12].”
• TextRank: Bringing Order into Text (2004, methodology): “, 2001) can be easily integrated into the TextRank model (Mihalcea, 2004).”