Multi-document Summarization Research Articles

PMCN: Combining PDF-modified Similarity and Complex Network in Multi-document Summarization

This study combines the concept of degree centrality in complex network with the Term Frequency * Proportional Document Frequency (TF*PDF) algorithm; the combined method, called TF-PDF, constructs relationship networks among sentences for writing news summaries. The TF-PDF method is a multi-document summarization extension of the ideas of Bun and Ishizuka (2002), who first published the TF*PDF algorithm for detecting hot topics. In their TF*PDF algorithm, Bun and Ishizuka defined the publisher of a news item as its channel . If the PDF weight of a term is higher than the weights of other terms, then the term is hotter than the other terms. However, this study attempts to develop summaries for news items. Because the TF*PDF algorithm summarizes daily news, TF-PDF replaces the concept of “channel” with “the date of the news event,” and uses the resulting chronicle ordering for a multi-document summarization algorithm, of which the F-measure scores were 0.042 and 0.051 higher than LexRank for the famous d30001t and d30003t tasks, respectively.

An Approach for Combining Multiple Weighting Schemes and Ranking Methods in Graph-Based Multi-Document Summarization

Automatic text summarization aims to reduce the document text size by building a brief and voluble summary that has the most important ideas in that document. Through the years, many approaches were proposed to improve the automatic text summarization results; the graph-based method for sentence ranking is considered one of the most important approaches in this field. However, most of these approaches rely on only one weighting scheme and one ranking method, which may cause some limitations in their systems. In this paper, we focus on combining multiple graph-based approaches to improve the results of generic, extractive, and multi-document summarization. This improvement results in more accurate summaries, which could be used as a significant part of some natural language applications. We develop and experiment with two graph-based approaches that combine four weighting schemes and two ranking methods in one graph framework. To combine these methods, we propose taking the average of their results using the arithmetic mean and the harmonic mean. We evaluate our proposed approaches using DUC 2003 & DUC 2004 dataset and measure the performance using ROUGE evaluation toolkit. Our experiments demonstrate that using the harmonic mean in combining weighting schemes outperform the arithmetic mean and show a good improvement over the baselines and many state-of-the-art systems.

SUMMARIZING INDONESIAN NEWS ARTICLES USING GRAPH CONVOLUTIONAL NETWORK

Multi-document summarization transforms a set of related documents into one concise summary. Existing Indonesian news articles summarizations do not take relationships between sentences into account and heavily depends on Indonesian language tools and resources. In this paper, we employ Graph Convolutional Network (GCN) which accepts word embedding sequence and sentence relationship graph as input for Indonesian news articles summarization. Our system is comprised of four main components, which are preprocess, graph construction, sentence scoring, and sentence selection components. Sentence scoring component is a neural network that uses Recurrent Neural Network (RNN) and GCN to produce the scores of all sentences. We use three different representation types for the sentence relationship graph. Sentence selection component then generates summary with two different techniques, which are by greedily choosing sentences with the highest scores and by using Maximum Marginal Relevance (MMR) technique. The evaluation shows that GCN summarizer with Personalized Discourse Graph (PDG) graph representation system achieves the best results with average ROUGE-2 recall score of 0.370 for 100-word summary and 0.378 for 200-word summary. Sentence selection using greedy technique gives better results for generating 100-word summary, while MMR performs better for generating 200-word summary.

MHLM Majority Voting Based Hybrid Learning Model for Multi-Document Summarization

Text summarization from multiple documents is an active research area in the current scenario as the data in the World Wide Web (WWW) is found in abundance. The text summarization process is time-consuming and hectic for the users to retrieve the relevant contents from this mass collection of the data. Numerous techniques have been proposed to provide the relevant information to the users in the form of the summary. Accordingly, this article presents the majority voting based hybrid learning model (MHLM) for multi-document summarization. First, the multiple documents are subjected to pre-processing, and the features, such as title-based, sentence length, numerical data and TF-IDF features are extracted for all the individual sentences of the document. Then, the feature set is sent to the proposed MHLM classifier, which includes the Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Neural Network (NN) classifiers for evaluating the significance of the sentences present in the document. These classifiers provide the significance scores based on four features extracted from the sentences in the document. Then, the majority voting model decides the significant texts based on the significance scores and develops the summary for the user and thereby, reduces the redundancy, increasing the quality of the summary similar to the original document. The experiment performed with the DUC 2002 data set is used to analyze the effectiveness of the proposed MHLM that attains the precision and recall at a rate of 0.94, f-measure at a rate of 0.93, and ROUGE-1 at a rate of 0.6324.

Extractive Incremental Multi-Document Summarization by Ranking Sentences Relevant to Key Phrase

Extractive Incremental Multi-Document Summarization by Ranking Sentences Relevant to Key Phrase

CIBS: A biomedical text summarizer using topic-based sentence clustering.

Automatic text summarizers can reduce the time required to read lengthy text documents by extracting the most important parts. Multi-document summarizers should produce a summary that covers the main topics of multiple related input texts to diminish the extent of redundant information. In this paper, we propose a novel summarization method named Clustering and Itemset mining based Biomedical Summarizer (CIBS). The summarizer extracts biomedical concepts from the input documents and employs an itemset mining algorithm to discover main topics. Then, it applies a clustering algorithm to put the sentences into clusters such that those in the same cluster share similar topics. Selecting sentences from all the clusters, the summarizer can produce a summary that covers a wide range of topics of the input text. Using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit, we evaluate the performance of the CIBS method against four summarizers including a state-of-the-art method. The results show that the CIBS method can improve the performance of single- and multi-document biomedical text summarization. It is shown that the topic-based sentence clustering approach can be effectively used to increase the informative content of summaries, as well as to decrease the redundant information.

MCRMR: Maximum coverage and relevancy with minimal redundancy based multi-document summarization

In this paper, we propose a novel extraction based method for multi-document summarization that covers three important features of a good summary: coverage, non-redundancy, and relevancy. The coverage and non-redundancy features are modeled to generate a single document from the multiple documents. These features are explored by the weighted combination of word embedding and Google based similarity methods. To accommodate the relevancy feature in the system generated summaries, the text summarization task is modeled as an optimization problem, where various text features with their optimized weights are used to score the sentences to find the relevant sentences. For features’ weight optimization, we use the meta-heuristic approach, Shark Smell Optimization (SSO). The experiments are performed on six benchmark datasets (DUC04, DUC06, DUC07, TAC08, TAC11, and MultiLing13) with the co-selection and content based performance parameters. The experimental results show that the proposed approach is viable and effective for multi-document summarization.

A Game Theory Approach for Multi-document Summarization

In today’s era, information has been growing exponentially on the web, due to which extraction of relevant and concise information has become a challenging task. To overcome the above problem, a fundamental tool known as summarization techniques has been used for understanding and organizing such large datasets. Recently, researchers have been devoting a lot of effort to develop semantics-based models, so as to improve summarization performance. In this paper, a versatile and principled game theory-based multi-document summarization framework integrated with Wikipedia ontology is proposed. The framework exploits the submodularity hidden in underlying ontology and is optimized using the proposed improved algorithm, to enhance the summarization performance. Results of the proposed approach were evaluated with the ROUGE evaluation metric for different multi-document summarization tasks against human-generated summaries and it outperformed DUC, TAC competitors, and other competitive methods.

Improving Extractive Multi-Document Text Summarization Through Multi-Objective Optimization

Multi-document summarization is an optimization problem demanding optimization of more than one objective function simultaneously. The proposed work regards balancing of the two significant objectives: content coverage and diversity when generating summaries from a collection of text documents. Any automatic text summarization system has the challenge of producing high quality summary. Despite the existing efforts on designing and evaluating the performance of many text summarization techniques, their formulations lack the introduction of any model that can give an explicit representation of – coverage and diversity – the two contradictory semantics of any summary . In this work, the design of generic text summarization model based on sentence extraction is redirected into more semantic measure reflecting individually both content coverage and content diversity as two explicit optimization models. The problem is defined by projecting the first criterion, i.e. content coverage in the light of text similarity. The proposed model hypothesizes a possible decomposition of text similarity into three different levels of optimization formula. First, aspire to global optimization, the candidate summary should cover the summary of the document collection. Then, to attain, less global optimization, the sentences of the candidate summary should cover the summary of the document collection. The third level of optimization is content with local optimization, where the difference between the magnitude of terms covered by the candidate summary and those of the document collection should be small. This coverage model is coupled with a proposed diversity model and defined as a Multi-Objective Optimization ( MOO ) problem. Moreover, heuristic perturbation and heuristic local repair operators have been proposed and injected into the adopted evolutionary algorithm to harness its strength. Assessment of the proposed model has been performed using document sets supplied by Document Understanding Conference 2002 ( ) and a comparison has been made with other state-of-the-art methods. Metric used to measure performance of the proposed work is Recall-Oriented Understudy for Gisting Evaluation ( ) toolkit. Results obtained support strong proof for the effectiveness and the significant performance awarded to the proposed MOO model over other state-of-the-art models.

Extractive multi-document summarization based on textual entailment and sentence compression via knapsack problem

AbstractBy increasing the amount of data in computer networks, searching and finding suitable information will be harder for users. One of the most widespread forms of information on such networks are textual documents. So exploring these documents to get information about their content is difficult and sometimes impossible. Multi-document text summarization systems are an aid to producing a summary with a fixed and predefined length, while covering the maximum content of the input documents. This paper presents a novel method for multi-document extractive summarization based on textual entailment relations and sentence compression via formulating the problem as a knapsack problem. In this approach, sentences of documents are ranked according to the extended Tf-Idf method, then entailment scores of selected sentences are computed. Through these scores, the final score of each sentence is calculated. Finally, by decreasing the lengths of sentences via sentence compression, the problem has been solved by greedy and dynamic Programming approaches to the knapsack problem. Experiments on standard summarization datasets and evaluating the results based on the Rouge system show that the suggested method, according to the best of our knowledge, has increased F-measure of query-based summarization systems by two per cent and F-measure of general summarization systems by five per cent.

Dual pattern-enhanced representations model for query-focused multi-document summarisation

To address the problem of query-focused multi-document summarisation, we present a novel unsupervised pattern-enhanced approach for representing coherent topics across documents, as well as the query relevance, in order to generate topically coherent summaries that meet the information needs of users. The proposed model employs not only a pattern-enhanced topic model to generate discriminative and semantic rich representations for topics and documents, but also a pattern-based relevance model for the query relevance of sentences. With these dual pattern-based representations for sentences, we are able to integrate various indicative metrics, such as rational coverage of document topics and sentence relevance, into a unified model. When evaluated on the datasets of the document understanding conferences of 2006 and 2007, the proposed approach shows a performance improvement as compared to a number of state-of-the-art methods and unsupervised baseline systems.

Topic and sentiment aware microblog summarization for twitter

Recent advances in microblog content summarization has primarily viewed this task in the context of traditional multi-document summarization techniques where a microblog post or their collection form one document. While these techniques already facilitate information aggregation, categorization and visualization of microblog posts, they fall short in two aspects: i) when summarizing a certain topic from microblog content, not all existing techniques take topic polarity into account. This is an important consideration in that the summarization of a topic should cover all aspects of the topic and hence taking polarity into account (sentiment) can lead to the inclusion of the less popular polarity in the summarization process. ii) Some summarization techniques produce summaries at the topic level. However, it is possible that a given topic can have more than one important aspect that need to have representation in the summarization process. Our work in this paper addresses these two challenges by considering both topic sentiments and topic aspects in tandem. We compare our work with the state of the art Twitter summarization techniques and show that our method is able to outperform existing methods on standard metrics such as ROUGE-1.

Multi-Documents Summarization Based on TextRank and its Application in Online Argumentation Platform

In an Online Argumentation Platform, a great deal of speech messages are produced. To find similar speech texts and extract their common summary is of great significance for improving the efficiency of argumentation and promoting consensus building. In this article, a method of speech text analysis is proposed. Firstly, a heuristic clustering algorithm is used to cluster the speech texts and obtain similar text sets. Then, an improved TextRank algorithm is used to extract a multi-document summary, and the results of the summary are fed back to experts (i.e. participants). The method of multi-document summarization is based on TextRank, which takes into account the position of sentences in paragraphs, the weight of the key sentence, and the length of the sentence. Finally, a prototype system is developed to verify the validity of the method using the four evaluation parameters of recall rate, accuracy rate, F-measure, and user feedback. The experimental results show that the method has a good performance in the system.

Solving Multi-Document Summarization as an Orienteering Problem

With advances in information technology, people face the problem of dealing with tremendous amounts of information and need ways to save time and effort by summarizing the most important and relevant information. Thus, automatic text summarization has become necessary to reduce the information overload. This article proposes a novel extractive graph-based approach to solve the multi-document summarization (MDS) problem. To optimize the coverage of information in the output summary, the problem is formulated as an orienteering problem and heuristically solved by an ant colony system algorithm. The performance of the implemented system (MDS-OP) was evaluated on DUC 2004 (Task 2) and MultiLing 2015 (MMS task) benchmark corpora using several ROUGE metrics, as well as other methods. Its comparison with the performances of 26 systems shows that MDS-OP achieved the best F-measure scores on both tasks in terms of ROUGE-1 and ROUGE-L (DUC 2004), ROUGE-SU4, and three other evaluation methods (MultiLing 2015). Overall, MDS-OP ranked among the best 3 systems.

Automatic Multi-Document Summarization Based on Keyword Density and Sentence-Word Graphs

As a fundamental and effective tool for document understanding and organization, multi-document summarization enables better information services by creating concise and informative reports for large collections of documents. In this paper, we propose a sentence-word two layer graph algorithm combining with keyword density to generate the multi-document summarization, known as Graph & Keywordρ. The traditional graph methods of multi-document summarization only consider the influence of sentence and word in all documents rather than individual documents. Therefore, we construct multiple word graph and extract right keywords in each document to modify the sentence graph and to improve the significance and richness of the summary. Meanwhile, because of the differences in the words importance in documents, we propose to use keyword density for the summaries to provide rich content while using a small number of words. The experiment results show that the Graph & Keywordρ method outperforms the state of the art systems when tested on the Duc2004 data set.

Sentence Relations for Extractive Summarization with Deep Neural Networks

Sentence regression is a type of extractive summarization that achieves state-of-the-art performance and is commonly used in practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to represent each sentence. In this article, we study the use of sentence relations, e.g., Contextual Sentence Relations (CSR), Title Sentence Relations (TSR), and Query Sentence Relations (QSR), so as to improve the performance of sentence regression. CSR, TSR, and QSR refer to the relations between a main body sentence and its local context, its document title, and a given query, respectively. We propose a deep neural network model, Sentence Relation-based Summarization (SRSum), that consists of five sub-models, PriorSum, CSRSum, TSRSum, QSRSum, and SFSum. PriorSum encodes the latent semantic meaning of a sentence using a bi-gram convolutional neural network. SFSum encodes the surface information of a sentence, e.g., sentence length, sentence position, and so on. CSRSum, TSRSum, and QSRSum are three sentence relation sub-models corresponding to CSR, TSR, and QSR, respectively. CSRSum evaluates the ability of each sentence to summarize its local contexts. Specifically, CSRSum applies a CSR-based word-level and sentence-level attention mechanism to simulate the context-aware reading of a human reader, where words and sentences that have anaphoric relations or local summarization abilities are easily remembered and paid attention to. TSRSum evaluates the semantic closeness of each sentence with respect to its title, which usually reflects the main ideas of a document. TSRSum applies a TSR-based attention mechanism to simulate people’s reading ability with the main idea (title) in mind. QSRSum evaluates the relevance of each sentence with given queries for the query-focused summarization. QSRSum applies a QSR-based attention mechanism to simulate the attentive reading of a human reader with some queries in mind. The mechanism can recognize which parts of the given queries are more likely answered by a sentence under consideration. Finally as a whole, SRSum automatically learns useful latent features by jointly learning representations of query sentences, content sentences, and title sentences as well as their relations. We conduct extensive experiments on six benchmark datasets, including generic multi-document summarization and query-focused multi-document summarization. On both tasks, SRSum achieves comparable or superior performance compared with state-of-the-art approaches in terms of multiple ROUGE metrics.

Novel Algorithm for Multi-document Summarization using Lexical Concept

Novel Algorithm for Multi-document Summarization using Lexical Concept

Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization

Automated multi-document extractive text summarization is a widely studied research problem in the field of natural language understanding. Such extractive mechanisms compute in some form the worthiness of a sentence to be included into the summary. While the conventional approaches rely on human crafted document-independent features to generate a summary, we develop a data-driven novel summary system called HNet, which exploits the various semantic and compositional aspects latent in a sentence to capture document independent features. The network learns sentence representation in a way that, salient sentences are closer in the vector space than non-salient sentences. This semantic and compositional feature vector is then concatenated with the document-dependent features for sentence ranking. Experiments on the DUC benchmark datasets (DUC-2001, DUC-2002 and DUC-2004) indicate that our model shows significant performance gain of around 1.5-2 points in terms of ROUGE score compared with the state-of-the-art baselines.

Sentence Extraction Based on Sentence Distribution and Part of Speech Tagging for Multi-Document Summarization

Automatic multi-document summarization needs to find representative sentences not only by sentence distribution to select the most important sentence but also by how informative a term is in a sentence. Sentence distribution is suitable for obtaining important sentences by determining frequent and well-spread words in the corpus but ignores the grammatical information that indicates instructive content. The presence or absence of informative content in a sentence can be indicated by grammatical information which is carried by part of speech (POS) labels. In this paper, we propose a new sentence weighting method by incorporating sentence distribution and POS tagging for multi-document summarization. Similarity-based Histogram Clustering (SHC) is used to cluster sentences in the data set. Cluster ordering is based on cluster importance to determine the important clusters. Sentence extraction based on sentence distribution and POS tagging is introduced to extract the representative sentences from the ordered clusters. The results of the experiment on the Document Understanding Conferences (DUC) 2004 are compared with those of the Sentence Distribution Method. Our proposed method achieved better results with an increasing rate of 5.41% on ROUGE-1 and 0.62% on ROUGE-2.

Sentence Extraction Based on Sentence Distribution and Part of Speech Tagging for Multi-Document Summarization

Sentence Extraction Based on Sentence Distribution and Part of Speech Tagging for Multi-Document Summarization