Extractive Summarization Using Supervised and Semi-Supervised Learning

By Kam-Fai Wong, Mingli Wu, Wenjie Li. 2008

238 citations recorded by the source corpus.

It is difficult to identify sentence importance from a single point of view. In this paper, we propose a learning-based approach to combine various sentence features. They are categorized as surface, content, relevance and event features. Surface features are related to extrinsic aspects of a sentence. Content features measure a sentence based on content-conveying words. Event features represent sentences by events they contained. Relevance features evaluate a sentence from its relatedness with other sentences. Experiments show that the combined features improved summarization performance significantly. Although the evaluation results are encouraging, supervised learning approach requires much labeled data. Therefore we investigate co-training by combining labeled and unlabeled data. Experiments show that this semi-supervised learning approach achieves comparable performance to its supervised counterpart and saves about half of the labeling time cost.

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, methodology): “A vast majority of the past work in summarization has been extractive, which consists of identifying key sentences or passages in the source document and reproducing them as summary (Neto et al., 2002; Erkan and Radev, 2004; Wong et al., 2008; Filippova and Altun, 2013; Colmenares et al., 2015).”
BanditSum: Extractive Summarization as a Contextual Bandit (2018, methodology): “Recently, neural network-based meth-ods have been gaining popularity over classical methods (Luhn, 1958; Gong and Liu, 2001; Con-roy and O’leary, 2001; Mihalcea and Tarau, 2004; Wong et al., 2008), as they have demonstrated stronger performance on large corpora.”
Deconvolutional Paragraph Representation Learning (2017, background): “For summarization tasks, [49] has considered a semi-supervised approach based on support vector machines, however, so far, research on semi-supervised text summarization using deep models is scarce.”
A New Approach to Improving Multilingual Summarization Using a Genetic Algorithm (2010, methodology): “Information retrieval and machine learning techniques were integrated to determine sentence importance (Kupiec et al., 1995; Wong et al., 2008).”
Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques (2020, background): “While early works focused on simply extracting important content from a document (Erkan and Radev, 2004; Wong et al., 2008), later approaches attempted to paraphrase the content into new sentences (abstractive summarization) (Filippova, 2010; Berg-Kirkpatrick et al.”
Im2Text: Describing Images Using 1 Million Captioned Photographs (2011, unknown): “Bad”
Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity Model (2017, background): “It is widely applicable to many NLP tasks including summarization (Wong et al., 2008; Nenkova et al., 2011), generation and question answering (Vo et al., 2015), paraphrase detection (Fernando and Stevenson, 2008), and machine translation (Corley and Mihalcea, 2005).”
Abstractive text summarization using LSTM-CNN based deep learning (2018, background): “Kam-Fai Wong [22] proposes a learning-based approach to combine various sentence features.”
A Survey of Text Summarization Techniques (2012, methodology): “Machine learning approaches to summarization offer great freedom because the number of indicators of importance is practically endless [40, 70, 104, 44, 27, 37, 99, 51].”
Cross-Language Document Summarization Based on Machine Translation Quality Prediction (2010, background): “Machine Learning based approaches have also been proposed for combining various sentence features (Wong et al., 2008).”
Efficient Summarization with Read-Again and Copy Mechanism (2016, background): “Notable examples are Neto et al. (2002), Erkan & Radev (2004), Wong et al. (2008), Filippova & Altun (2013) and Colmenares et al. (2015).”
Text Summarization Techniques: A Brief Survey (2017, methodology): “[78] proposed a semi-supervised method for extractive summarization.”
Semi-supervised Classification for Natural Language Processing (2014, methodology): “s applicable to text classiﬁcation but the performance depends on the labeled and unlabeled training data, and the source from which the data are derived. C. Extractive Text Summarization Wong et al. [16] have conducted a comparative study where they produced extractive summaries by using both super”