Document Summarization Using Conditional Random Fields

By Dou Shen, Hua Li, Qiang Yang, Zheng Chen. International Joint Conference on Artificial Intelligence, 2007

387 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/bb88d2460070a1157165b86e93f3ed61878adef8

How researchers see this paper

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

Citations in the corpus

HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space (2015, methodology): “For performing an automatic evaluation of the headlines generated by our system we follow the path taken by related work such as Zajic et al. (2004) and use a subset of the ROUGE metrics for comparing candidate headlines with reference ones, which have been proven to strongly correlate with human ev”
A Survey of Text Summarization Techniques (2012, methodology): “This assumption is apparently not realistic, and methods that explicitly encode dependencies between sentences such as Hidden Markov Models and Conditional Random Fields outperform other learning methods [14, 30, 83].”
A new sentence similarity measure and sentence based extractive technique for automatic text summarization (2009, methodology): “In spite of the fact that among our criterion functions the worst result is obtained by criterion function F 2 , but it shows better result than the methods CRF, SVM and Manifold–Ranking.”
Multiple documents summarization based on evolutionary optimization algorithm (2013, methodology): “Other methods include NMF-based topic specification (Lee, Park, Ahn, & Kim, 2009; Wang et al., 2008, 2009) and CRF-based summarization (Shen et al., 2007).”
Text Summarization Techniques: A Brief Survey (2017, methodology): “It turns out that methods explicitly assuming the dependency between sentences such as Hidden Markov model [18] and Conditional Random Fields [65] often outperform other techniques.”
New Alignment Methods for Discriminative Book Summarization (2013, methodology): “Following previous work, we devise sentencelevel features that can be readily computed in comparison both with the document in which the sentence in found, and in comparison with the collection of documents as whole (Yeh et al., 2005; Shen et al., 2007).”
Jointly Learning to Extract and Compress (2011, background): “For example, many models learn to score each input sentence independently (Teufel and Moens, 1997; Shen et al., 2007; Schilder and Kondadadi, 2008), and then assemble extractive summaries from the top-ranked sentences in a way not incorporated into the learning process.”
SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents (2016, methodology): “For example, (Shen et al. 2007) used Conditional Random Fields to binary-classify sentences sequentially.”
Ranking Sentences for Extractive Summarization with Reinforcement Learning (2018, background): “A vast majority of these methods learn to score each sentence independently (Barzilay and Elhadad, 1997; Teufel and Moens, 1997; Erkan and Radev, 2004; Mihalcea and Tarau, 2004; Shen et al., 2007; Schilder and Kondadadi, 2008; Wan, 2010) and a summary is generated by selecting top-scored sentences i”
Cross-language document summarization via extraction and ranking of multiple summaries (2019, methodology): “centroid-based method [20], integer linear programming (ILP) [9], submodular function maximization [13–15], graph-based methods [5,24], and supervised learning-based methods [4,17,18,21].”
Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization (2008, methodology): “Current document summarization methods usually involve natural language processing and machine learning techniques [29, 2, 34], such as classification, clustering, conditional random fields (CRF), etc.”
Recent advances in document summarization (2017, background): “As a result, hidden Markov models [37], conditional random fields [170], structural SVMs [109] have all been applied in such settings.”
Text Classification Algorithms: A Survey (2019, methodology): “However, these techniques are mostly used for document summarization [25] and automatic keyword extraction [26].”