ArA*summarizer: An Arabic text summarization system based on subtopic segmentation and using an A* algorithm for reduction

Automatic text summarization is a field situated at the intersection of natural language processing and information retrieval. Its main objective is to automatically produce a condensed representative form of documents. This paper presents ArA*summarizer, an automatic system for Arabic single document summarization. The system is based on an unsupervised hybrid approach that combines statistical, cluster-based, and graph-based techniques. The main idea is to divide text into subtopics then select the most relevant sentences in the most relevant subtopics. The selection process is done by an A* algorithm executed on a graph representing the different lexical–semantic relationships between sentences. Experimentation is conducted on Essex Arabic summaries corpus and using recall-oriented understudy for gisting evaluation, automatic summarization engineering, merged model graphs, and n-gram graph powered evaluation via regression evaluation metrics. The evaluation results showed the good performance of our system compared with existing works.     

A hybrid machine learning model for multi-document summarization

This work proposes an approach that uses statistical tools to improve content selection in multi-document automatic text summarization. The method uses a trainable summarizer, which takes into account several features: the similarity of words among sentences, the similarity of words among paragraphs, the text format, cue-phrases, a score related to the frequency of terms in the whole document, the title, sentence location and the occurrence of non-essential information. The effect of each of these sentence features on the summarization task is investigated. These features are then used in combination to construct text summarizer models based on a maximum entropy model, a naive-Bayes classifier, and a support vector machine. To produce the final summary, the three models are combined into a hybrid model that ranks the sentences in order of importance. The performance of this new method has been tested using the DUC 2002 data corpus. The effectiveness of this technique is measured using the ROUGE score, and the results are promising when compared with some existing techniques.     

一种基于演化算法进行句子抽取的多文档自动摘要系统SBGA

SBGA系统将多文档自动摘要过程视为一个从源文档集中抽取句子的组合优化过程,并用演化算法来求得近似最优解。与基于聚类的句子抽取方法相比,基于演化算法进行句子抽取的方法是面向摘要整体的,因此能获得更好的近似最优摘要。演化算法的评价函数中考虑了衡量摘要的4个标准:长度符合用户要求、信息覆盖率高、更多地保留原文传递的重要信息、无冗余。另外,为了提高词频计算的精度, SBGA采用了一种改进的词频计算方法TFS,将加权后词的同义词频率加到了原词频中。在DUC2004测试数据集上的实验结果表明,基于演化算法进行句子抽取的方法有很好的性能,其ROUGE-1分值比DUC2004最优参赛系统仅低0.55%。改进的词频计算方法TFS对提高文档质量也起到了良好的作用。     

An unsupervised approach to generating generic summaries of documents

We present an optimization-based unsupervised approach to automatic document summarization. In the proposed approach, text summarization is modeled as a Boolean programming problem. This model generally attempts to optimize three properties, namely, (1) relevance: summary should contain informative textual units that are relevant to the user; (2) redundancy: summaries should not contain multiple textual units that convey the same information; and (3) length: summary is bounded in length. The approach proposed in this paper is applicable to both tasks: single- and multi-document summarization. In both tasks, documents are split into sentences in preprocessing. We select some salient sentences from document(s) to generate a summary. Finally, the summary is generated by threading all the selected sentences in the order that they appear in the original document(s). We implemented our model on multi-document summarization task. When comparing our methods to several existing summarization methods on an open DUC2005 and DUC2007 data sets, we found that our method improves the summarization results significantly. This is because, first, when extracting summary sentences, this method not only focuses on the relevance scores of sentences to the whole sentence collection, but also the topic representative of sentences. Second, when generating a summary, this method also deals with the problem of repetition of information. The methods were evaluated using ROUGE-1, ROUGE-2 and ROUGE-SU4 metrics. In this paper, we also demonstrate that the summarization result depends on the similarity measure. Results of the experiment showed that combination of symmetric and asymmetric similarity measures yields better result than their use separately.     

GenDocSum + MCLR: Generic document summarization based on maximum coverage and less redundancy

With the rapid growth of information on the Internet and electronic government recently, automatic multi-document summarization has become an important task. Multi-document summarization is an optimization problem requiring simultaneous optimization of more than one objective function. In this study, when building summaries from multiple documents, we attempt to balance two objectives, content coverage and redundancy. Our goal is to investigate three fundamental aspects of the problem, i.e. designing an optimization model, solving the optimization problem and finding the solution to the best summary. We model multi-document summarization as a Quadratic Boolean Programing (QBP) problem where the objective function is a weighted combination of the content coverage and redundancy objectives. The objective function measures the possible summaries based on the identified salient sentences and overlap information between selected sentences. An innovative aspect of our model lies in its ability to remove redundancy while selecting representative sentences. The QBP problem has been solved by using a binary differential evolution algorithm. Evaluation of the model has been performed on the DUC2002, DUC2004 and DUC2006 data sets. We have evaluated our model automatically using ROUGE toolkit and reported the significance of our results through 95% confidence intervals. The experimental results show that the optimization-based approach for document summarization is truly a promising research direction.     

Multi-document summarization via Archetypal Analysis of the content-graph joint model

In recent years, algebraic methods, more precisely matrix decomposition approaches, have become a key tool for tackling document summarization problem. Typical algebraic methods used in multi-document summarization (MDS) vary from soft and hard clustering approaches to low-rank approximations. In this paper, we present a novel summarization method AASum which employs the archetypal analysis for generic MDS. Archetypal analysis (AA) is a promising unsupervised learning tool able to completely assemble the advantages of clustering and the flexibility of matrix factorization. In document summarization, given a content-graph data matrix representation of a set of documents, positively and/or negatively salient sentences are values on the data set boundary. These extreme values, archetypes, can be computed using AA. While each sentence in a data set is estimated as a mixture of archetypal sentences, the archetypes themselves are restricted to being sparse mixtures, i.e., convex combinations of the original sentences. Since AA in this way readily offers soft clustering, we suggest to consider it as a method for simultaneous sentence clustering and ranking. Another important argument in favor of using AA in MDS is that in contrast to other factorization methods, which extract prototypical, characteristic, even basic sentences, AA selects distinct (archetypal) sentences and thus induces variability and diversity in produced summaries. Experimental results on the DUC generic summarization data sets evidence the improvement of the proposed approach over the other closely related methods.     

GA, MR, FFNN, PNN and GMM based models for automatic text summarization

This work proposes an approach to address the problem of improving content selection in automatic text summarization by using some statistical tools. This approach is a trainable summarizer, which takes into account several features, including sentence position, positive keyword, negative keyword, sentence centrality, sentence resemblance to the title, sentence inclusion of name entity, sentence inclusion of numerical data, sentence relative length, Bushy path of the sentence and aggregated similarity for each sentence to generate summaries. First, we investigate the effect of each sentence feature on the summarization task. Then we use all features in combination to train genetic algorithm (GA) and mathematical regression (MR) models to obtain a suitable combination of feature weights. Moreover, we use all feature parameters to train feed forward neural network (FFNN), probabilistic neural network (PNN) and Gaussian mixture model (GMM) in order to construct a text summarizer for each model. Furthermore, we use trained models by one language to test summarization performance in the other language. The proposed approach performance is measured at several compression rates on a data corpus composed of 100 Arabic political articles and 100 English religious articles. The results of the proposed approach are promising, especially the GMM approach.     

权衡熵和相关度的自动摘要技术研究

生成高质量的文档摘要需要用简约而不丢失信息的描述文档,是自动摘要技术的一大难题。该文认为高质量的文档摘要必须尽量多的覆盖原始文档中的信息,同时尽可能的保持紧凑。从这一角度出发,从文档中抽取出熵和相关度这两组特征用以权衡摘要的信息覆盖率和紧凑性。该文采用基于回归的有监督摘要技术对提取的特征进行权衡,并且采用单文档摘要和多文档摘要进行了系统的实验。实验结果证明对于单文档摘要和多文档摘要,权衡熵和相关度均能有效地提高文档摘要的质量。     

Concept generalization and fusion for abstractive sentence generation

Text summarization is either extractive or abstractive. Extractive summarization is to select the most salient pieces of information (words, phrases, and/or sentences) from a source document without adding any external information. Abstractive summarization allows an internal representation of the source document so as to produce a faithful summary of the source. In this case, external text can be inserted into the generated summary. Because of the complexity of the abstractive approach, the vast majority of work in text summarization has adopted an extractive approach.In this work, we focus on concepts fusion and generalization, i.e. where different concepts appearing in a sentence can be replaced by one concept which covers the meanings of all of them. This is one operation that can be used as part of an abstractive text summarization system. The main goal of this contribution is to enrich the research efforts on abstractive text summarization with a novel approach that allows the generalization of sentences using semantic resources. This work should be useful in intelligent systems more generally since it introduces a means to shorten sentences by producing more general (hence abstractions of the) sentences. It could be used, for instance, to display shorter texts in applications for mobile devices. It should also improve the quality of the generated text summaries by mentioning key (general) concepts. One can think of using the approach in reasoning systems where different concepts appearing in the same context are related to one another with the aim of finding a more general representation of the concepts. This could be in the context of Goal Formulation, expert systems, scenario recognition, and cognitive reasoning more generally.We present our methodology for the generalization and fusion of concepts that appear in sentences. This is achieved through (1) the detection and extraction of what we define as generalizable sentences and (2) the generation and reduction of the space of generalization versions. We introduce two approaches we have designed to select the best sentences from the space of generalization versions. Using four NLTK¹ corpora, the first approach estimates the “acceptability” of a given generalization version. The second approach is Machine Learning-based and uses contextual and specific features. The recall, precision and F1-score measures resulting from the evaluation of the concept generalization and fusion approach are presented.     

基于局部话题句群的事件相关多文档摘要研究

多文档自动文摘研究的目的是给用户提供简洁全面的文档信息并提高用户获取信息的效率。在进行局部话题确定时,通常是利用聚类分析的方法把相似的文本单元聚成一个局部话题。该文提出了一种针对新闻事件的多文档摘要生成方法,其特色在于：在提取基本新闻要素和扩展新闻要素的基础上分别形成了基本局部话题句群（BPTSG）和扩展局部话题句群（EPTSG）,这样可以在尽可能全面地覆盖多个话题的同时缩减自身的冗余。此外,文中还提出了一种基于事件时间和句子位置信息的文摘句排序方法。实验结果验证了该文所提的方法是有效的,与基于聚类的自动文摘系统相比较,该系统生成的摘要质量有显著提高。     

Recent advances in document summarization

The task of automatic document summarization aims at generating short summaries for originally long documents. A good summary should cover the most important information of the original document or a cluster of documents, while being coherent, non-redundant and grammatically readable. Numerous approaches for automatic summarization have been developed to date. In this paper we give a self-contained, broad overview of recent progress made for document summarization within the last 5 years. Specifically, we emphasize on significant contributions made in recent years that represent the state-of-the-art of document summarization, including progress on modern sentence extraction approaches that improve concept coverage, information diversity and content coherence, as well as attempts from summarization frameworks that integrate sentence compression, and more abstractive systems that are able to produce completely new sentences. In addition, we review progress made for document summarization in domains, genres and applications that are different from traditional settings. We also point out some of the latest trends and highlight a few possible future directions.     

Extractive single-document summarization based on genetic operators and guided local search

Due to the exponential growth of textual information available on the Web, end users need to be able to access information in summary form – and without losing the most important information in the document when generating the summaries. Automatic generation of extractive summaries from a single document has traditionally been given the task of extracting the most relevant sentences from the original document. The methods employed generally allocate a score to each sentence in the document, taking into account certain features. The most relevant sentences are then selected, according to the score obtained for each sentence. These features include the position of the sentence in the document, its similarity to the title, the sentence length, and the frequency of the terms in the sentence. However, it has still not been possible to achieve a quality of summary that matches that performed by humans and therefore methods continue to be brought forward that aim to improve on the results. This paper addresses the generation of extractive summaries from a single document as a binary optimization problem where the quality (fitness) of the solutions is based on the weighting of individual statistical features of each sentence – such as position, sentence length and the relationship of the summary to the title, combined with group features of similarity between candidate sentences in the summary and the original document, and among the candidate sentences of the summary. This paper proposes a method of extractive single-document summarization based on genetic operators and guided local search, called MA-SingleDocSum. A memetic algorithm is used to integrate the own-population-based search of evolutionary algorithms with a guided local search strategy. The proposed method was compared with the state of the art methods UnifiedRank, DE, FEOM, NetSum, CRF, QCS, SVM, and Manifold Ranking, using ROUGE measures on the datasets DUC2001 and DUC2002. The results showed that MA-SingleDocSum outperforms the state of the art methods.     

Creating a reference data set for the summarization of discussion forum threads

In this paper we address extractive summarization of long threads in online discussion fora. We present an elaborate user evaluation study to determine human preferences in forum summarization and to create a reference data set. We showed long threads to ten different raters and asked them to create a summary by selecting the posts that they considered to be the most important for the thread. We study the agreement between human raters on the summarization task, and we show how multiple reference summaries can be combined to develop a successful model for automatic summarization. We found that although the inter-rater agreement for the summarization task was slight to fair, the automatic summarizer obtained reasonable results in terms of precision, recall, and ROUGE. Moreover, when human raters were asked to choose between the summary created by another human and the summary created by our model in a blind side-by-side comparison, they judged the model’s summary equal to or better than the human summary in over half of the cases. This shows that even for a summarization task with low inter-rater agreement, a model can be trained that generates sensible summaries. In addition, we investigated the potential for personalized summarization. However, the results for the three raters involved in this experiment were inconclusive. We release the reference summaries as a publicly available dataset.     

基于局部主题关键句抽取的自动文摘方法

自动文摘是语言信息处理中的重要环节。该文提出一种基于局部主题关键句抽取的中文自动文摘方法。通过层次分割的方法对文档进行主题分割,从各个局部主题单元中抽取一定数量的句子作为文章的文摘句。通过事先对文档进行语义分析,有效地避免了数据冗余和容易忽略分布较小的主题等问题。实验结果表明了该方法的有效性。     

iSpreadRank: Ranking sentences for extraction-based summarization using feature weight propagation in the sentence similarity network

Sentence extraction is a widely adopted text summarization technique where the most important sentences are extracted from document(s) and presented as a summary. The first step towards sentence extraction is to rank sentences in order of importance as in the summary. This paper proposes a novel graph-based ranking method, iSpreadRank, to perform this task. iSpreadRank models a set of topic-related documents into a sentence similarity network. Based on such a network model, iSpreadRank exploits the spreading activation theory to formulate a general concept from social network analysis: the importance of a node in a network (i.e., a sentence in this paper) is determined not only by the number of nodes to which it connects, but also by the importance of its connected nodes. The algorithm recursively re-weights the importance of sentences by spreading their sentence-specific feature scores throughout the network to adjust the importance of other sentences. Consequently, a ranking of sentences indicating the relative importance of sentences is reasoned. This paper also develops an approach to produce a generic extractive summary according to the inferred sentence ranking. The proposed summarization method is evaluated using the DUC 2004 data set, and found to perform well. Experimental results show that the proposed method obtains a ROUGE-1 score of 0.38068, which represents a slight difference of 0.00156, when compared with the best participant in the DUC 2004 evaluation.     

A complex network approach to text summarization

Automatic summarization of texts is now crucial for several information retrieval tasks owing to the huge amount of information available in digital media, which has increased the demand for simple, language-independent extractive summarization strategies. In this paper, we employ concepts and metrics of complex networks to select sentences for an extractive summary. The graph or network representing one piece of text consists of nodes corresponding to sentences, while edges connect sentences that share common meaningful nouns. Because various metrics could be used, we developed a set of 14 summarizers, generically referred to as CN-Summ, employing network concepts such as node degree, length of shortest paths, d-rings and k-cores. An additional summarizer was created which selects the highest ranked sentences in the 14 systems, as in a voting system. When applied to a corpus of Brazilian Portuguese texts, some CN-Summ versions performed better than summarizers that do not employ deep linguistic knowledge, with results comparable to state-of-the-art summarizers based on expensive linguistic resources. The use of complex networks to represent texts appears therefore as suitable for automatic summarization, consistent with the belief that the metrics of such networks may capture important text features.     

Assessing sentence scoring techniques for extractive text summarization

Text summarization is the process of automatically creating a shorter version of one or more text documents. It is an important way of finding relevant information in large text libraries or in the Internet. Essentially, text summarization techniques are classified as Extractive and Abstractive. Extractive techniques perform text summarization by selecting sentences of documents according to some criteria. Abstractive summaries attempt to improve the coherence among sentences by eliminating redundancies and clarifying the contest of sentences. In terms of extractive summarization, sentence scoring is the technique most used for extractive text summarization. This paper describes and performs a quantitative and qualitative assessment of 15 algorithms for sentence scoring available in the literature. Three different datasets (News, Blogs and Article contexts) were evaluated. In addition, directions to improve the sentence extraction results obtained are suggested.     

MCMR: Maximum coverage and minimum redundant text summarization model

In paper, we propose an unsupervised text summarization model which generates a summary by extracting salient sentences in given document(s). In particular, we model text summarization as an integer linear programming problem. One of the advantages of this model is that it can directly discover key sentences in the given document(s) and cover the main content of the original document(s). This model also guarantees that in the summary can not be multiple sentences that convey the same information. The proposed model is quite general and can also be used for single- and multi-document summarization. We implemented our model on multi-document summarization task. Experimental results on DUC2005 and DUC2007 datasets showed that our proposed approach outperforms the baseline systems.     

自动文本摘要方法

自动文本摘要是继信息检索之后信息或知识获取的一个重要步骤,对高质量的文档文摘十分重要。该文提出以句子为基本抽取单位,以位置和标题关键词为句子的加权特征,对句子基于潜语义聚类,提出语义结构的摘要方法。同时给出了较为客观和有效的摘要评价方法。实验表明了该方法的有效性。     

Extractive multi-document summarization using population-based multicriteria optimization

Multi-document summarization is the process of extracting salient information from a set of source texts and present that information to the user in a condensed form. In this paper, we propose a multi-document summarization system which generates an extractive generic summary with maximum relevance and minimum redundancy by representing each sentence of the input document as a vector of words in Proper Noun, Noun, Verb and Adjective set. Five features, such as TF_ISF, Aggregate Cross Sentence Similarity, Title Similarity, Proper Noun and Sentence Length associated with the sentences, are extracted, and scores are assigned to sentences based on these features. Weights that can be assigned to different features may vary depending upon the nature of the document, and it is hard to discover the most appropriate weight for each feature, and this makes generation of a good summary a very tough task without human intelligence. Multi-document summarization problem is having large number of decision parameters and number of possible solutions from which most optimal summary is to be generated. Summary generated may not guarantee the essential quality and may be far from the ideal human generated summary. To address this issue, we propose a population-based multicriteria optimization method with multiple objective functions. Three objective functions are selected to determine an optimal summary, with maximum relevance, diversity, and novelty, from a global population of summaries by considering both the statistical and semantic aspects of the documents. Semantic aspects are considered by Latent Semantic Analysis (LSA) and Non Negative Matrix Factorization (NMF) techniques. Experiments have been performed on DUC 2002, DUC 2004 and DUC 2006 datasets using ROUGE tool kit. Experimental results show that our system outperforms the state of the art works in terms of Recall and Precision.