Text summarization via hidden Markov models
By John M. Conroy, Dianne P. O'Leary. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001
399 citations recorded by the source corpus.
A sentence extract summary of a document is a subset of the document's sentences that contains the main ideas in the document. We present an approach to generating such summaries, a hidden Markov model that judges the likelihood that each sentence should be contained in the summary. We compare the results of this method with summaries generated by humans, showing that we obtain significantly higher agreement than do earlier methods.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/1c5d41ba83fb57b5fb5af81fac956154c9ff0ce4
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
Citations in the corpus
- HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization (2019, methodology): “It is usually modeled as a sentence ranking problem by using the scores from classifiers (Kupiec et al., 1995), sequential labeling models (Conroy and O’leary, 2001) as well as integer linear programmers (Woodsend and Lapata, 2010).”
- Document Summarization Using Conditional Random Fields (2007, methodology): “Given an observation sequence (sentence sequence here) X = (x1, . . . , xT ) and the corresponding state sequence Y = (y1, . . . , yT ), the probability of Y conditioned on X defined in CRFs, P (Y |X), is as follows: 1 ZX exp ∑ i,k λkfk(yi−1, yi, X) + ∑ i,l µlgl(yi, X) (1) where ZX is the…”
- A Survey on Automatic Text Summarization (2007, methodology): “…the sentence in the document (built into the state structure of the HMM), number of terms in the sentence, and likeliness of the sentence terms given the document terms. no 3 2 1 no no no Figure 1: Markov model to extract to three summary sentences from a document (Conroy and O'leary, 2001 ).”
- Text summarization using unsupervised deep learning (2017, methodology): “Machine learning techniques have widely used for text summarization (Li et al., 2009; Ouyang et al., 2011; Conroy and O’leary, 2001; Corston-Oliver et al., 2004).”
- Objective Function Learning to Match Human Judgements for Optimization-Based Summarization (2018, methodology): “Previous work focused on predicting sentence (Conroy and O’leary, 2001; Cao et al., 2015) or n-gram (Hong and Nenkova, 2014; Li et al., 2013) scores and then defining a composition function to get a score for the summary.”
- Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization (2008, methodology): “Other methods include NMF-based topic speci(cid:12)c summarization [24], CRF-based summarization [29], and hidden Markov model (HMM) based method [5].”
- BanditSum: Extractive Summarization as a Contextual Bandit (2018, methodology): “Recently, neural network-based methods have been gaining popularity over classical methods (Luhn, 1958; Gong and Liu, 2001; Conroy and O’leary, 2001; Mihalcea and Tarau, 2004; Wong et al., 2008), as they have demonstrated stronger performance on large corpora.”
- 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.”
- How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature (2019, background): “Here is a list of the most cited ‘summarization’ papers of that period according to Google Scholar (Erkan and Radev, 2004; Radev et al., 2004; Gong and Liu, 2001; Conroy and O’leary, 2001; Lin and Hovy, 2000; Mihalcea, 2004; Goldstein et al., 2000).”
- 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.”
- 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].”
- Content Selection in Deep Learning Models of Summarization (2018, methodology): “We model the sentence extraction task as a sequence tagging problem, following (Conroy and O’Leary, 2001).”
- Neural Document Summarization by Jointly Learning to Score and Select Sentences (2018, methodology): “Conroy and O’leary (2001) further use a Hidden Markov Model in document summarization.”