Graph-Based Keyword Extraction for Single-Document Summarization

By Marina Litvak, Mark Last. 2008

316 citations recorded by the source corpus.

In this paper, we introduce and compare between two novel approaches, supervised and unsupervised, for identifying the keywords to be used in extractive summarization of text documents. Both our approaches are based on the graph-based syntactic representation of text and web documents, which enhances the traditional vector-space model by taking into account some structural document features. In the supervised approach, we train classification algorithms on a summarized collection of documents with the purpose of inducing a keyword identification model. In the unsupervised approach, we run the HITS algorithm on document graphs under the assumption that the top-ranked nodes should represent the document keywords. Our experiments on a collection of benchmark summaries show that given a set of summarized training documents, the supervised classification provides the highest keyword identification accuracy, while the highest F-measure is reached with a simple degree-based ranking. In addition, it is sufficient to perform only the first iteration of HITS rather than running it to its convergence.

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond (2016, background): “In order to accomplish this goal, we may need to go beyond the word-embeddings-based representation of the input document and capture additional linguistic features such as parts-of-speech tags, named-entity tags, and TF and IDF statistics of the words.”
Self reinforcement for important passage retrieval (2013, methodology): “Closely related to our work are the unsupervised key phrase extraction approaches that have been explored to reinforce summarization [32, 29, 11, 22, 24].”
A New Approach to Improving Multilingual Summarization Using a Genetic Algorithm (2010, background): “, 1997), sentences (Luhn, 1958), keyphrases (Turney, 2000) or keywords (Litvak and Last, 2008).”
Main Core Retention on Graph-of-Words for Single-Document Keyword Extraction (2015, methodology): “The edges were drawn between terms co-occurring within a fixed-size sliding window W of size 4 over the processed text, value consistently reported as working well [3,7,16,19,22].”
TopicRank: Graph-Based Topic Ranking for Keyphrase Extraction (2013, background): “Keyphrases are useful in many tasks such as information retrieval (Medelyan and Witten, 2008), document summarization (Litvak and Last, 2008) or document clustering (Han et al.”
Clustering to Find Exemplar Terms for Keyphrase Extraction (2009, methodology): “The work in (Litvak and Last, 2008) applies HITS algorithm on the word graph of a document under the assumption that the top-ranked nodes should be the document keywords.”
PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents (2017, background): “Nodes are then ranked us-ing graph centrality measures such as PageRank (Mihalcea and Tarau, 2004; Liu et al., 2010) or HITS (Litvak and Last, 2008), and the top ranked phrases are returned as keyphrases.”