DUC2002 Datasets Research Articles

TG-SMR: A Text Summarization Algorithm Based on Topic and Graph Models

Recently, automation is considered vital in most fields since computing methods have a significant role in facilitating work such as automatic text summarization. However, most of the computing methods that are used in real systems are based on graph models, which are characterized by their simplicity and stability. Thus, this paper proposes an improved extractive text summarization algorithm based on both topic and graph models. The methodology of this work consists of two stages. First, the well-known TextRank algorithm is analyzed and its shortcomings are investigated. Then, an improved method is proposed with a new computational model of sentence weights. The experimental results were carried out on standard DUC2004 and DUC2006 datasets and compared to four text summarization methods. Finally, through experiments on the DUC2004 and DUC2006 datasets, our proposed improved graph model algorithm TG-SMR (Topic Graph-Summarizer) is compared to other text summarization systems. The experimental results prove that the proposed TG-SMR algorithm achieves higher ROUGE scores. It is foreseen that the TG-SMR algorithm will open a new horizon that concerns the performance of ROUGE evaluation indicators.

Single document text summarization addressed with a cat swarm optimization approach.

The availability of a tremendous amount of online information bringing about a broad interest in extracting relevant information in a compact and meaningful way, prompted the need for automatic text summarization. Hence, in the proposed system, the automated text summarization has been considered as an extractive single-document summarization problem, and a Cat Swarm Optimization (CSO) algorithm-based approach is proposed to solve it, whose objective is to generate good summaries in terms of content coverage, informative, anti-redundancy, and readability. In this work, input documents are pre-processed first. Then the cat population is initialized, where each individual (cat) in a binary vector is randomly initialized in the search space, considering the constraint. The objective function is then formulated considering different sentence quality measures. The Best Cat Memory Pool (BCMP) is initialized based on the objective function score. After that, individuals are randomly distributed for position updating to perform seeking/tracing mode operations based on the mixture ratio in each iteration. BCMP is also updated accordingly. Finally, an optimal individual is chosen to generate the summary after the last iteration. DUC-2001 and DUC-2002 data sets and ROUGE measures are used for system evaluation, and the obtained results are compared with the various state-of-the-art methods. We have achieved approximately 25% and 5% improvement on ROUGE-1 and ROUGE-2 scores on the datasets over the best existing method mentioned in this paper, revealing the proposed method’s superiority. The proposed system is also evaluated considering the generational distance, CPU processing time, cohesion, and readability factor, reflecting that the system-generated summaries are readable, concise, relevant, and fast. We have also conducted a two-sample t-test, and one-way ANOVA test showing the proposed approach is statistically significant.

Multi-Document Text Summarization Using Deep Belief Network

Recently, there is a lot of information available on the Internet, which makes it difficult for users to find what they're looking for. Extractive text summarization methods are designed to reduce the amount of text in a document collection by focusing on the most important information and reducing the redundant information. Summarizing documents should not affect the main ideas and the meaning of the original text. This paper proposes a new automatic, generic, and extractive multi-document summarizing model aiming at producing a sufficiently informative summary. The idea of the proposed model is based on extracting nine different features from each sentence in the document collection. The extracted features are introduced as input to the Deep Belief Network (DBN) for the classification purpose as either important or unimportant sentences. Only, the important sentences pass to the next phase to construct a graph. The PageRank algorithm is used to assign scores to the graph sentences. The sentences with high scores were selected to create a summary document. The performance of the proposed model was evaluated using the DUC-2004 (Task2) dataset using ROUGE more. The experimental results demonstrate that our proposed model is more effective than the baseline method and some state-of-the-art methods, Where ROUGE-1 reached 0.4032 and ROUGE-2 to 0.1021.

Single document summarization using the information from documents with the same topic

The essence of extractive summarization is to measure the importance of sentences in the document. When extracting summary from a single document, it is difficult to comprehensively and effectively evaluate the importance of sentences due to the lack of information. In this paper, we propose a kind of single document summarization method using information from documents under the same topic. This method integrates the topic information from neighborhood documents and statistical information from the target document to calculate the score of sentences. Then the scoring results are used as a prior scores for each sentence in the target document. After the target document is represented by the sentence graph, the final score of the sentences are obtained by the biased random walk algorithm. Finally, the Maximal Marginal Relevance (MMR) algorithm is used to select the sentences to form summary. The experimental results on the DUC2001 and DUC2002 datasets show that the effect of extracting summary is improved by incorporating information from the documents under the same topic.

Sentiment Lossless Summarization

The aim of automatic text summarization (ATS) is to extract representative texts from documents and keep major points of the extracted texts consistent with the original documents. However, most existing studies ignore sentimental information loss in the summarization process, which leads to sentiment loss summarization. To address the sentiment loss issue during summarization, we introduce a sentiment compensation mechanism into document summarization and propose a graph-based extractive summarization approach named Sentiment Lossless Summarization (SLS). SLS first creates a graph representation for a document to obtain the importance score (i.e., literal indicator) of each sentence. Second, sentiment dictionaries are leveraged to analyze the sentence sentiments. Third, during each summarization iteration, the sentences with the lowest scores are iteratively removed, and the sentiment compensation weights of the remaining sentences are updated. With the help of sentiment compensation during the summarization process, sentiment consistencies between candidate summaries and the original documents are maintained. Intrinsic evaluations conducted on the DUC2001, DUC2002, DUC2004, and Multi-News datasets demonstrate that our approach outperforms baselines and state-of-the-art summarization methods in terms of Recall-Oriented Understudy for Gisting Evaluation (ROUGE) scores. Additionally, to further evaluate SLS performance in sentiment retention, extrinsic evaluations are introduced, and summary quality in terms of sentiment loss is evaluated by measuring the prediction accuracy for sentiment polarities of either movie (IMDb dataset) or product (Amazon dataset) review summaries. The experimental results demonstrate that our approach can improve prediction accuracy by at most 6% compared to the baseline.

Text Summarization as a Multi-objective Optimization Task: Applying Harmony Search to Extractive Multi-Document Summarization

Abstract Today, automated extractive text summarization is one of the most common techniques for organizing information. In extractive summarization, the most appropriate sentences are selected from the text and build a representative summary. Therefore, probing for the best sentences is a fundamental task. This paper has coped with extractive summarization as a multi-objective optimization problem and proposed a language-independent, semantic-aware approach that applies the harmony search algorithm to generate appropriate multi-document summaries. It learns the objective function from an extra set of reference summaries and then generates the best summaries according to the trained function. The system also performs some supplementary activities for better achievements. It expands the sentences by using an inventive approach that aims at tuning conceptual densities in the sentences towards important topics. Furthermore, we introduced an innovative clustering method for identifying important topics and reducing redundancies. A sentence placement policy based on the Hamiltonian shortest path was introduced for producing readable summaries. The experiments were conducted on DUC2002, DUC2006 and DUC2007 datasets. Experimental results showed that the proposed framework could assist the summarization process and yield better performance. Also, it was able to generally outperform other cited summarizer systems.

A semantic approach to extractive multi-document summarization: Applying sentence expansion for tuning of conceptual densities

Today, due to a vast amount of textual data, automated extractive text summarization is one of the most common and practical techniques for organizing information. Extractive summarization selects the most appropriate sentences from the text and provide a representative summary. The sentences, as individual textual units, usually are too short for major text processing techniques to provide appropriate performance. Hence, it seems vital to bridge the gap between short text units and conventional text processing methods.In this study, we propose a semantic method for implementing an extractive multi-document summarizer system by using a combination of statistical, machine learning based, and graph-based methods. It is a language-independent and unsupervised system. The proposed framework learns the semantic representation of words from a set of given documents via word2vec method. It expands each sentence through an innovative method with the most informative and the least redundant words related to the main topic of sentence. Sentence expansion implicitly performs word sense disambiguation and tunes the conceptual densities towards the central topic of each sentence. Then, it estimates the importance of sentences by using the graph representation of the documents. To identify the most important topics of the documents, we propose an inventive clustering approach. It autonomously determines the number of clusters and their initial centroids, and clusters sentences accordingly. The system selects the best sentences from appropriate clusters for the final summary with respect to information salience, minimum redundancy, and adequate coverage.A set of extensive experiments on DUC2002 and DUC2006 datasets was conducted for investigating the proposed scheme. Experimental results showed that the proposed sentence expansion algorithm and clustering approach could considerably enhance the performance of the summarization system. Also, comparative experiments demonstrated that the proposed framework outperforms most of the state-of-the-art summarizer systems and can impressively assist the task of extractive text summarization.

A two-step abstractive summarization model with asynchronous and enriched-information decoding

Most sequence-to-sequence abstractive summarization models generate the summaries based on the source article and the generated words, but they often neglect the future information implied in the un-generated words, which means that they lack the ability of “lookahead.” In this paper, we present a novel summarization model with “lookahead” ability to fully employ the implied future information. Our model takes two steps: (1) in the first step, an asynchronous decoder model with a no ground truth guiding backward decoder that explicitly produces and exploits the future information is trained. (2) in the inference process, in addition to the joint probability of the generated sequence, an enriched-information decoding method is proposed to further take future ROUGE reward of the un-generated words into account. Furthermore, the future ROUGE reward is predicted by a novel reward-predict model, and it takes the hidden states of the pre-trained asynchronous decoder model as input. Experimental results show that our two-step summarization model achieves new state-of-the-art results on CNN/Daily Mail dataset and the generalization of our model on test-only DUC-2002 datasets achieves higher scores than the state-of-the-art model.

MAMHOA: a multi-agent meta-heuristic optimization algorithm with an approach for document summarization issues

Today, given the increasing volume of information and the difficulty of using them for specific applications such as email, websites, news, etc., the use of automated information summarization algorithms has become more popular than traditional algorithms. Taking advantage of computer algorithms, these algorithms produce a summary of information while retaining its original meaning. However, given its semantic and structural properties as well as the variable comparative parameters of information, the summarization process is considered as an NP-hard problem. Therefore, to solve these problems it is better to use meta-heuristic algorithms, which are generally inspired by the behavior of nature. These meta-heuristic algorithms help to better solve the hard problems through producing optimum solutions. In this paper, we propose an optimization algorithm named multi-agent meta-heuristic optimization algorithm (MAMHOA) for extractive text summarization. MAMHOA is a combination of biogeography-based optimization (BBO) algorithm and multi-agent systems concepts to generate an optimum summary. Several computational tests are used to evaluate the effectiveness and efficiency of the proposed algorithm, which is compared to other algorithms provided in the literature. MAMHOA and other algorithms are tested on DUC2002 datasets and attained solutions are analyzed using ROUGE metrics. From the results obtained, it can be seen that the proposed algorithm is more effective and efficient than those mentioned in the literature i.e. Baseline and state-of-the-art methods for different ROUGE metrics.

Incorporating word attention with convolutional neural networks for abstractive summarization

Neural sequence-to-sequence (seq2seq) models have been widely used in abstractive summarization tasks. One of the challenges of this task is redundant contents in the input document often confuses the models and leads to poor performance. An efficient way to solve this problem is to select salient information from the input document. In this paper, we propose an approach that incorporates word attention with multilayer convolutional neural networks (CNNs) to extend a standard seq2seq model for abstractive summarization. First, by concentrating on a subset of source words during encoding an input sentence, word attention is able to extract informative keywords in the input, which gives us the ability to interpret generated summaries. Second, these keywords are further distilled by multilayer CNNs to capture the coarse-grained contextual features of the input sentence. Thus, the combined word attention and multilayer CNNs modules provide a better-learned representation of the input document, which helps the model generate interpretable, coherent and informative summaries in an abstractive summarization task. We evaluate the effectiveness of our model on the English Gigaword, DUC2004 and Chinese summarization dataset LCSTS. Experimental results show the effectiveness of our approach.

Neural abstractive summarization fusing by global generative topics

Various efforts have been dedicated to automatically generate coherent, condensed and informative summaries. Most concentrate on improving the capability of generating neural language models locally, but do not consider global information. In real cases, a summary is comprehensively influenced by the full content of the source text and is especially guided by its core sense. To seamlessly integrate global semantic representation into a summarization generation system, we propose to incorporate a neural generative topic matrix as an abstractive level of topic information. By mapping global semantics into a local generative language model, the abstractive summarization is capable of generating succinct and recapitulative words or phrases. Extensive experiments on DUC-2004 and Gigaword datasets convincingly validate the proposed model.

COSUM: Text summarization based on clustering and optimization

AbstractText summarization is a process of extracting salient information from a source text and presenting that information to the user in a condensed form while preserving its main content. In the text summarization, most of the difficult problems are providing wide topic coverage and diversity in a summary. Research based on clustering, optimization, and evolutionary algorithm for text summarization has recently shown good results, making this a promising area. In this paper, for a text summarization, a two‐stage sentences selection model based on clustering and optimization techniques, called COSUM, is proposed. At the first stage, to discover all topics in a text, the sentences set is clustered by using k‐means method. At the second stage, for selection of salient sentences from clusters, an optimization model is proposed. This model optimizes an objective function that expressed as a harmonic mean of the objective functions enforcing the coverage and diversity of the selected sentences in the summary. To provide readability of a summary, this model also controls length of sentences selected in the candidate summary. For solving the optimization problem, an adaptive differential evolution algorithm with novel mutation strategy is developed. The method COSUM was compared with the 14 state‐of‐the‐art methods: DPSO‐EDASum; LexRank; CollabSum; UnifiedRank; 0–1 non‐linear; query, cluster, summarize; support vector machine; fuzzy evolutionary optimization model; conditional random fields; MA‐SingleDocSum; NetSum; manifold ranking; ESDS‐GHS‐GLO; and differential evolution, using ROUGE tool kit on the DUC2001 and DUC2002 data sets. Experimental results demonstrated that COSUM outperforms the state‐of‐the‐art methods in terms of ROUGE‐1 and ROUGE‐2 measures.

Skeleton to Abstraction: An Attentive Information Extraction Schema for Enhancing the Saliency of Text Summarization

Current popular abstractive summarization is based on an attentional encoder-decoder framework. Based on the architecture, the decoder generates a summary according to the full text that often results in the decoder being interfered by some irrelevant information, thereby causing the generated summaries to suffer from low saliency. Besides, we have observed the process of people writing summaries and find that they write a summary based on the necessary information rather than the full text. Thus, in order to enhance the saliency of the abstractive summarization, we propose an attentive information extraction model. It consists of a multi-layer perceptron (MLP) gated unit that pays more attention to the important information of the source text and a similarity module to encourage high similarity between the reference summary and the important information. Before the summary decoder, the MLP and the similarity module work together to extract the important information for the decoder, thus obtaining the skeleton of the source text. This effectively reduces the interference of irrelevant information to the decoder, therefore improving the saliency of the summary. Our proposed model was tested on CNN/Daily Mail and DUC-2004 datasets, and achieved a 42.01 ROUGE-1 f-score and 33.94 ROUGE-1, recall respectively. The result outperforms the state-of-the-art abstractive model on the same dataset. In addition, by subjective human evaluation, the saliency of the generated summaries was further enhanced.

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.

A Model for Text Summarization

Text summarization is a process for creating a concise version of document(s) preserving its main content. In this paper, to cover all topics and reduce redundancy in summaries, a two-stage sentences selection method for text summarization is proposed. At the first stage, to discover all topics the sentences set is clustered by using k-means method. At the second stage, optimum selection of sentences is proposed. From each cluster the salient sentences are selected according to their contribution to the topic (cluster) and their proximity to other sentences in cluster to avoid redundancy in summaries until the appointed summary length is reached. Sentence selection is modeled as an optimization problem. In this study, to solve the optimization problem an adaptive differential evolution with novel mutation strategy is employed. With a test on benchmark DUC2001 and DUC2002 data sets, the ROUGE value of summaries got by the proposed approach demonstrated its validity, compared to the traditional methods of sentence selection and the top three performing systems for DUC2001 and DUC2002.

Multi-document summarization using closed patterns

There are two main categories of multi-document summarization: term-based and ontology-based methods. A term-based method cannot deal with the problems of polysemy and synonymy. An ontology-based approach addresses such problems by taking into account of the semantic information of document content, but the construction of ontology requires lots of manpower. To overcome these open problems, this paper presents a pattern-based model for generic multi-document summarization, which exploits closed patterns to extract the most salient sentences from a document collection and reduce redundancy in the summary. Our method calculates the weight of each sentence of a document collection by accumulating the weights of its covering closed patterns with respect to this sentence, and iteratively selects one sentence that owns the highest weight and less similarity to the previously selected sentences, until reaching the length limitation. The sentence weight calculation by patterns reduces the dimension and captures more relevant information. Our method combines the advantages of the term-based and ontology-based models while avoiding their weaknesses. Empirical studies on the benchmark DUC2004 datasets demonstrate that our pattern-based method significantly outperforms the state-of-the-art methods. Multi-document summarization can be used to extract a particular individual's opinions in the form of closed patterns, from this individual's documents shared in social networks, hence provides a useful tool for further analyzing the individual's behavior and influence in group activities.

Feature Priority Based Sentence Filtering Method for Extractive Automatic Text Summarization

Abstract Due to increasing amount of text data available on internet it becomes difficult for users to get the desired information quickly. In order to reduce this access time a summary could be utilized generated using Automatic Text Summarization. In general it could be extractive or abstractive. For extractive text summarization in which representative sentences from the document itself are selected as summary, various statistical, knowledge based and discourse based methods are proposed by researchers. In this paper we explored feature based extractive approaches for text summarization. We proposed a feature priority based filtering method for summarization. For this purpose we used sentence location as main feature and other features in priority to filter the redundant sentences. Experimental results on DUC2002 datasets shows that our method performs uniformly as compared to the best results for particular combination of features.

Topic aspect-oriented summarization via group selection

The summarization is desirable to efficiently apprehend the gist of the huge amount of data and becomes a significant challenge in many applications such as news article summarization and social media mining. Considering the summaries from multi-documents of one topic can describe various aspects of one given topic, this paper attempts to exploit appropriate priors to generate topic aspect-oriented summarization (abbreviated as TAOS). The underlying intuition of the proposed TAOS is that different topics can prefer different aspects and the different aspects can be represented by different preference of features(e.g., technical topic may prefer proper noun than sports topic). In order to materialize the intuition of TAOS, we first extract several groups of features according to topic factors, and then a group norm penalty (i.e., ℓ1/ℓ2 norm) and latent variables are utilized to select overlapping groups of features. We compare our proposed approach with some state-of-the-art methods on DUC2003, DUC2004 datasets for text summarization and NUS-Wide dataset for image summarization. The results show our method can generate meaningful summarization in terms of ROUGE and Jensen–Shannon Divergence metrics.

Multiple documents summarization based on evolutionary optimization algorithm

This paper proposes an optimization-based model for generic document summarization. The model generates a summary by extracting salient sentences from documents. This approach uses the sentence-to-document collection, the summary-to-document collection and the sentence-to-sentence relations to select salient sentences from given document collection and reduce redundancy in the summary. To solve the optimization problem has been created an improved differential evolution algorithm. The algorithm can adjust crossover rate adaptively according to the fitness of individuals. We implemented the proposed model on multi-document summarization task. Experiments have been performed on DUC2002 and DUC2004 data sets. The experimental results provide strong evidence that the proposed optimization-based approach is a viable method for document summarization.

Formulation of document summarization as a 0–1 nonlinear programming problem

We proposed a novel text summarization model based on 0–1 non-linear programming problem. This proposed model covers the main content of the given document(s) through sentence assignment. We implemented our model on multi-document summarization task. When comparing our method to several existing summarization methods on an open DUC2001 and DUC2002 datasets, we found that the proposed method could improve the summarization results significantly. The methods were evaluated using ROUGE-1, ROUGE-2 and ROUGE-W metrics.