检索结果-内蒙古大学图书馆

33rd Annual ACM Symposium on Applied Computing (ACM SAC)

作者： Garcia, Rodrigo Lima, Rinaldo Espinasse, Bernard Oliveira, Hilario Univ Fed Rural Pernambuco Recife PE Brazil Aix Marseille Univ LSIS UMR CNRS Marseille France Univ Fed Pernambuco Recife PE Brazil

ISBN: (纸本)9781450351911

Automatic Text summarization (ATS) is a viable option to reduce the content of textual documents, e.g., as a possible preprocessing step in many text mining applications. single-document extractive summarizers have been developed based on different approaches, but many of them have the drawback of producing summaries with low coherence among the selected sentences in the generated summaries. In this paper, we present an unsupervised summarization system as an attempt towards coherent extractive single-document summarization. This system relies on Integer Linear Programming (ILP) as an optimization technique for selecting the smallest subset of sentences of a document maximizing the coverage of relevant concepts. Furthermore, our solution uses a graph-based algorithm for two goals: representing both sentences and concepts and enabling local coherence scoring among the sentences in the generated summaries. The proposed system is evaluated on two single-document benchmark datasets (DUC 2001-2002) using ROUGE measures, and compared with other state-of-the-art summarizers. The achieved results are very competitive.

关键词： single-document summarization Extractive summarization Coherence Entity Graph Integer Linear Programming

来源：评论

学校读者我要写书评

暂无评论

The CNN-Corpus: A Large Textual Corpus for single-document Extractive summarization 19

The CNN-Corpus: A Large Textual Corpus for Single-Document E...

引用

19th ACM Symposium on document Engineering (DocEng)

作者： Lins, Rafael Dueire Oliveira, Hilario Cabral, Luciano Batista, Jamilson Tenorio, Bruno Ferreira, Rafael Lima, Rinaldo Pereira e Silva, Gabriel de Franca Simske, Steven J. Univ Fed Pernambuco Recife PE Brazil Univ Fed Rural Pernambuco Recife PE Brazil Colorado State Univ Ft Collins CO 80523 USA

ISBN: (纸本)9781450368872

This paper details the features and the methodology adopted in the construction of the CNN-corpus, a test corpus for single document extractive text summarization of news articles. The current version of the CNN-corpus encompasses 3,000 texts in English, and each of them has an abstractive and an extractive summary. The corpus allows quantitative and qualitative assessments of extractive summarization strategies.

关键词： single-document summarization Corpus Extractive summarization Multi-language summarization

来源：评论

学校读者我要写书评

暂无评论

A Concept-based Integer Linear Programming Approach for single-document summarization 5

A Concept-based Integer Linear Programming Approach for Sing...

引用

5th Brazilian Conference on Intelligent Systems (BRACIS)

作者： Oliveira, Hilario Lima, Rinaldo Lins, Rafael Dueire Freitas, Fred Riss, Marcelo Simske, Steven J. Univ Fed Pernambuco Informat Ctr Recife PE Brazil HP Brazil R&D Porto Alegre RS Brazil HP Labs Ft Collins CO 80528 USA

ISBN: (纸本)9781509035663

Automatic single-document summarization is a process that receives a single input document and outputs a condensed version with only the most relevant information. This paper proposes an unsupervised concept-based approach for single-document summarization using Integer Linear Programming (ILP). Such an approach maximizes the coverage of the important concepts in the summary, avoiding redundancy, and taking into consideration some readability aspects of the generated summary as well. A new weighting method that combines both coverage and position of the sentences is proposed to estimate the importance of a concept. Moreover, a weighted distribution strategy that prioritizes sentences at the beginning of the document if they have relevant concepts is investigated. The readability of the generated summaries is improved by the inclusion of constraints into the ILP model to avoid dangling coreferences and breaks in the normal discourse flow of the document. Experimental results on the DUC 2001-2002 and the CNN corpora demonstrated that the proposed approach is competitive with state-of-the-art summarizers evaluated regarding the traditional ROUGE scores.

关键词： Automatic Text summarization Concept-based approach Integer Linear Programming single-document summarization

来源：评论

学校读者我要写书评

暂无评论

Assessing shallow sentence scoring techniques and combinations for single and multi-document summarization

引用

EXPERT SYSTEMS WITH APPLICATIONS 2016年 65卷 68-86页

作者： Oliveira, Hilario Ferreira, Rafael Lima, Rinaldo Lins, Rafael Dueire Freitas, Fred Riss, Marcelo Simske, Steven J. Univ Fed Pernambuco Recife PE Brazil Univ Fed Rural Pernambuco Recife PE Brazil HP Brazil Porto Alegre RS Brazil HP Labs Ft Collins CO 80528 USA

The volume of text data has been growing exponentially in the last years, mainly due to the Internet. Automatic Text summarization has emerged as an alternative to help users find relevant information in the content of one or more documents. This paper presents a comparative analysis of eighteen shallow sentence scoring techniques to compute the importance of a sentence in the context of extractive single and multi-document summarization. Several experiments were made to assess the performance of such techniques individually and applying different combination strategies. The most traditional benchmark on the news domain demonstrates the feasibility of combining such techniques, in most cases outperforming the results obtained by isolated techniques. Combinations that perform competitively with the state-of-the-art systems were found. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Automatic text summarization Extractive-based approaches Sentence scoring techniques single-document summarization Multi-document summarization

来源：评论

学校读者我要写书评

暂无评论

Analyzing Preprocessing Settings for Urdu single-document Extractive summarization 10

Analyzing Preprocessing Settings for Urdu Single-document Ex...

引用

10th International Conference on Language Resources and Evaluation (LREC)

作者： Humayoun, Muhammad Yu, Hwanjo Univ Paul Sabatier IRIT Toulouse France Pohang Univ Sci & Technol POSTECH Dept Comp Sci & Engn Pohang South Korea

ISBN: (纸本)9782951740891

Preprocessing is a preliminary step in many fields including IR and NLP. The effect of basic preprocessing settings on English for text summarization is well-studied. However, there is no such effort found for the Urdu language (with the best of our knowledge). In this study, we analyze the effect of basic preprocessing settings for single-document text summarization for Urdu, on a benchmark corpus using various experiments. The analysis is performed using the state-of-the-art algorithms for extractive summarization and the effect of stopword removal, lemmatization, and stemming is analyzed. Results showed that these pre-processing settings improve the results.

关键词： automatic text summarization single-document summarization extraction based summarization benchmark experiments preprocessing

来源：评论

学校读者我要写书评

暂无评论

Extractive single-document summarization Based on Global-Best Harmony Search and a Greedy Local Optimizer 14th

Extractive Single-Document Summarization Based on Global-Bes...

引用

14th Mexican International Conference on Artificial Intelligence (MICAI)

作者： Mendoza, Martha Cobos, Carlos Leon, Elizabeth Univ Cauca Popayan Colombia Univ Nacl Colombia Bogota Colombia

ISBN: (纸本)9783319271019;9783319271002

Due to the great amount of documents available on the Web, end users need to be able to access information in summary form - keeping the most important information in the document. The methods employed for automatic text summarization 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. In this paper, the extractive single document summarization task is treated as a binary optimization problem and, based on the Global-best Harmony Search metaheuristic and a greedy local search procedure, a new algorithm called ESDS-GHS-GLO is proposed. This algorithm optimizes an objective function, which is a lineal normalized combination of the position of the sentence in the document, sentence length, and coverage of the selected sentences in the summary. The proposed method was compared with the state of the art methods MA-singleDocSum, DE, FEOM, UnifiedRank, Net-Sum, QCS, CRF, SVM, and Manifold Ranking, using ROUGE measures on the DUC2001 and DUC2002 datasets. The results showed that ESDS-GHS-GLO outperforms most of the state-of-the-art methods except MA-singleDocSum. ESDS-GHS-GLO obtains promissory results using a fitness function less complex than MA-singleDocSum, therefore requiring less execution time.

关键词： single-document summarization Memetic algorithms Global-best harmony search Greedy search

来源：评论

学校读者我要写书评

暂无评论

Gibberish, Assistant, or Master? Using Tweets Linking to News for Extractive single -document summarization 15

Gibberish, Assistant, or Master? Using Tweets Linking to New...

引用

38th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Wei, Zhongyu Gao, Wei Univ Texas Dallas 800 W Campbell Rd Richardson TX 75080 USA Qatar Fdn Qatar Comp Res Inst Doha Qatar

ISBN: (纸本)9781450336215

single-document summarization is a challenging task. In this paper, we explore effective ways using the tweets linking to news for generating extractive summary of each document. We reveal the very basic value of tweets that can be utilized by regarding every tweet as a vote for candidate sentences. Base on such finding, we resort to unsupervised summarization models by leveraging the linking tweets to master the ranking of candidate extracts via random walk on a heterogeneous graph. The advantage is that we can use the linking tweets to opportunistically "supervise" the summarization with no need of reference summaries. Furthermore, we analyze the influence of the volume and latency of tweets on the quality of output summaries since tweets come after news release. Compared to truly supervised summarizer unaware of tweets, our method achieves significantly better results with reasonably small tradeoff on latency;compared to the same using tweets as auxiliary features, our method is comparable while needing less tweets and much shorter time to achieve significant outperformance.

关键词： single-document summarization tweets highlights

来源：评论

学校读者我要写书评

暂无评论

single document summarization using word and sentence embeddings

Single document summarization using word and sentence embedd...

引用

2015 Joint International Mechanical,Electronic and Information Technology Conference(JIMET 2015)

作者： Ayana Department of Computer Science and Technology Tsinghua University Department of Computer Information Management Inner Mongolia University of Finance and Economics

ISBN: (纸本)9781510817982

Automatic document summarization has become increasingly important in the age of big data. However, traditional summarization systems have two major weaknesses: term-vector data sparsity and semantic information deficiency. In this paper, we solve these problems by adopting word and sentence embeddings, whose distributed nature enables the relation establishment between words and sentences. Experimental result shows that our models outperform two state-of-the-art graph based summarization systems.

关键词： single-document summarization Word Embeddings Sentence Embeddings

来源：评论

学校读者我要写书评

暂无评论

Abstractive Indonesian News summarization Using BERT2GPT 7

Abstractive Indonesian News Summarization Using BERT2GPT

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Nasari, Maulin Maulina, Ayu Girsang, Abba Suganda Computer Science Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350382266

This study examines the necessity of employing BERT2GPT for single-document summarization in the current age of escalating digital data. The primary focus of this work is on the abstractive technique, which tries to generate versatile summaries that surpass the primary sentences of the original content. This study employs two models, namely BERT and GPT -2, for the purpose of the summarization system. The paper introduces the BERT2GPT model, which merges the bidirectional characteristics of BERT with the generative powers of GPT. The findings indicate that the BERT2GPT method successfully catches significant information and linguistic nuances, hence enhancing the quality of the generated summaries. The corresponding average values for Rl, R2, and RL are 0.62, 0.56, and 0.60, respectively. © 2023 IEEE.

关键词： Abstractive summarization BERT2GPT single-document summarization

来源：评论

学校读者我要写书评

暂无评论

EdgeSumm: Graph-based framework for automatic text summarization

引用

INFORMATION PROCESSING & MANAGEMENT 2020年第6期57卷 102264-102264页

作者： El-Kassas, Wafaa S. Salama, Cherif R. Rafea, Ahmed A. Mohamed, Hoda K. Ain Shams Univ Fac Engn Dept Comp & Syst Engn Cairo Egypt Amer Univ Cairo Dept Comp Sci & Engn Cairo Egypt

Searching the Internet for a certain topic can become a daunting task because users cannot read and comprehend all the resulting texts. Automatic Text summarization (ATS) in this case is clearly beneficial because manual summarization is expensive and time-consuming. To enhance ATS for single documents, this paper proposes a novel extractive graph-based framework "EdgeSumm" that relies on four proposed algorithms. The first algorithm constructs a new text graph model representation from the input document. The second and third algorithms search the constructed text graph for sentences to be included in the candidate summary. When the resulting candidate summary still exceeds a user-required limit, the fourth algorithm is used to select the most important sentences. EdgeSumm combines a set of extractive ATS methods (namely graph-based, statistical-based, semantic-based, and centrality-based methods) to benefit from their advantages and overcome their individual drawbacks. EdgeSumm is general for any document genre (not limited to a specific domain) and unsupervised so it does not require any training data. The standard datasets DUC2001 and DUC2002 are used to evaluate EdgeSumm using the widely used automatic evaluation tool: Recall-Oriented Understudy for Gisting Evaluation (ROUGE). EdgeSumm gets the highest ROUGE scores on DUC2001. For DUC2002, the evaluation results show that the proposed framework outperforms the state-of-the-art ATS systems by achieving improvements of 1.2% and 4.7% over the highest scores in the literature for the metrics of ROUGE-1 and ROUGE-L respectively. In addition, EdgeSumm achieves very competitive results for the metrics of ROUGE-2 and ROUGE-SU4.

关键词： Automatic text summarization Extractive text summarization Graph representation model single-document summarization EdgeSumm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：