ROUGE (Recall-Oriented Understudy for Gisting Evaluation) 2015


Resources:

  • berouge.com .. software package for automated evaluation of summaries

Wikipedia:

References:

See also:

ROUGE (Recall-Oriented Understudy for Gisting Evaluation) 2014


Comparing semantic models for evaluating automatic document summarization M Campr, K Ježek – International Conference on Text, Speech, and …, 2015 – Springer … summarization. ROUGE [2] (Recall-Oriented Understudy for Gisting Evaluation) includes measures for automatically determining the qual- ity of system summaries by comparing them to ideal human-made summaries. These … Cited by 6 Related articles All 6 versions

Lexical cohesion and entailment based segmentation for arabic text summarization (lceas) F AL-Khawaldeh, V Samawi – The World of Computer Science and …, 2015 – oaji.net … Each system output is compared against Essex Arabic Summaries Corpus (EASC) corpus (the model summaries), using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) and Automatic Summarization Engineering (AutoSummEng) metrics. … Cited by 6 Related articles All 6 versions

A new multi-layered approach for automatic text summaries mono-document based on social spiders MA Boudia, RM Hamou, A Amine, ME Rahmani… – … on Computer Science …, 2015 – Springer … The Evaluation Measure Recall – Oriented Understudy for Gisting Evaluation We evaluate the results of this work by the measure called Recall – Oriented Unders- tudy for Gisting Evaluation (ROUGE) proposed by (Lin, 2004) involving the differ- ences between distributions of … Cited by 3 Related articles All 3 versions

A Hierarchical Tree Model for Update Summarization R Li, H Shindo – European Conference on Information Retrieval, 2015 – Springer … For each topic, two doc- sets, D H and D U are given1. As for the automatic evaluation, we use the widely used ROUGE (Recall Oriented Understudy for Gisting Evaluation) (Lin and Hovy, 2003) measures, including ROUGE-2 and ROUGE-SU4. … Cited by 2 Related articles

A study on the use of word embeddings and pagerank for vietnamese text summarization V Phung, L De Vine – Proceedings of the 20th Australasian Document …, 2015 – dl.acm.org … The structure of the paper is as follows. Section 2 briefly describes some related works. Section 3 provides an intro- 1ROUGE stands for Recall Oriented Understudy for Gisting Evaluation, see section 5.3 for definition Page 2. … Cited by 2 Related articles All 2 versions

Twitter Event Summarization Using Phrase Reinforcement Algorithm and NLP Features G Mane, A Kulkarni – International Journal of Advanced …, 2015 – pdfs.semanticscholar.org … Chin-Yew Lin[8] has presented ROUGE: A Package for Automatic Evaluation of Summaries. ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. … ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. … Cited by 1 Related articles

Automatic Multi-Document Arabic Text Summarization Using Clustering and Keyphrase Extraction, 1–9 HN Fejer, N Omar – Journal of Artificial Intelligence, 2015 – docsdrive.com … These algorithms are applied to extract one sentence from a group of similar sentences while ignoring the other similar sentences. The Recall-Oriented Understudy for Gisting Evaluation (ROGUE) metrics were used for the evaluation. … Cited by 1 Related articles All 3 versions

Evaluation of Automatic Text Summarizations based on Human Summaries F Kiyoumarsi – Procedia-Social and Behavioral Sciences, 2015 – Elsevier … To overcome these shortcomings, we employed a package, ROUGE, for automatic evaluation of summaries. ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. … Lin, C.-Y., 2003. ROUGE: Recall-oriented understudy for gisting evaluation. … Cited by 1 Related articles

Automatic summarization of polish news articles by sentence selection K Jassem, ? Pawluczuk – Computer Science and Information …, 2015 – ieeexplore.ieee.org … V. EVALUATION A. Evaluation method ROUGE (DUC conference) ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation [2]. It was introduced by Chin-Yew Lin at Doc- ument Understanding Conference (DUC) in 2004 and since then it has became the standard … Cited by 2 Related articles All 7 versions

A New Biomimetic Method Based on the Power Saves of Social Bees for Automatic Summaries of Texts by Extraction MA Boudia, RM Hamou, A Amine… – International Journal of …, 2015 – igi-global.com … 4.2.1. The Evaluation Measure Recall: Oriented Understudy for Gisting Evaluation (ROUGE) The evaluation of abstracts can be done semi-automatically through measures of similarities computed between a candidate summary and one or more reference summaries. … Cited by 1 Related articles All 2 versions

Cluster Priority Based Sentence Ranking For Efficient Extractive Text Summaries YK Meena, D Gopalani – pdfs.semanticscholar.org … While generating summary, if total words in summary are exceeded the value 100, sentence inclusion is stopped. We used Recall-Oriented Understudy for Gisting Evaluation (ROUGE) [20] matrices to evaluate quality of generated summaries. ? ? ? ? … Related articles

A New Approach Based On The Detection Of Opinion By Sentiwordnet For Automatic Text Summaries By Extraction RM HAMOU, MA BOUDIA, A AMINE – airccj.org … The second step of our experiment will begin to study is a robustness of summary, we use two evaluation method ROUGE-SU (2) (Recall-Oriented Understudy for Gisting Evaluation –Skip Unit) and F-measure. Page 8. 170 Computer Science & Information Technology (CS & IT) … Related articles All 3 versions

Bilingual Text Summarization RMB Sayed – 2015 – fayoum.edu.eg … We use standard set of documents used for testing purposes and available on the web. For evaluating our system, we used Recall-Oriented Understudy for Gisting Evaluation (ROUGE) scores. ROUGE is a method to measure the quality of the summary using a manually …

Data-Driven Unsupervised Evaluation of Automatic Text Summarization Systems E Yagunova, O Makarova, E Pronoza – Mexican International Conference …, 2015 – Springer … be conducted in real time. A common intrinsic approach towards text summarization systems evaluation is represented by the ROUGE (Recall-Oriented Understudy for Gisting Evaluation) metric. There are about 20 variations … Related articles

Text Summarization Using Particle Swarm Optimization Algorithm ABDEY MAHJOUB – 2015 – repository.sustech.edu … PSO – Particle Swarm Optimization GA – Genetic Algorithm ACO – Ant colony optimization ROUGE – Recall-Oriented Understudy for Gisting Evaluation DUC – Document Understanding Conference AVG-P – Average Precision AVG-R – Average Recall AVG-F – Average F-measure … Related articles

A survey on existing extractive techniques for query-based text summarization N Rahman, B Borah – Advanced Computing and …, 2015 – ieeexplore.ieee.org … intrinsic method [30]. In this case ROUGE (Recall-Oriented Understudy for Gisting Evaluation) toolkit is widely used as it is supposed to produce the most reliable and stable scores compared to human evaluation. ROUGE is … Related articles All 2 versions

Text Summarization by using Genetic Algorithm Method? AA Mohammed – 2015 – repository.sustech.edu … NIST – National Institute of Standards and Technology ROUGE – Recall-Oriented Understudy for Gisting Evaluation DUC – Document Understanding Conference … 2.4.2 ROUGE: methodology of evaluation The ROUGE (Recall-Oriented Understudy for Gisting Evaluation) is a …

Automatic Summarization of News Articles in Mobile Devices L Cabral, R Lima, R Lins, M Neto… – Artificial Intelligence …, 2015 – ieeexplore.ieee.org … Thus, researchers look for quantitative assessment methods for evaluating the final generated summaries [5]. In this context, ROUGE (Recall-Oriented Understudy for Gisting Evaluation) [16] consists of a set of metrics implemented as a software package used for evaluating … Cited by 1 Related articles All 3 versions

Automatic broadcast news summarization via rank classifiers and crowdsourced annotation S Parthasarathy, T Hasan – Acoustics, Speech and Signal …, 2015 – ieeexplore.ieee.org … their relative quality [10]. The fact that multiple good summaries can exist is also well known and considered in calculating the ROUGE (Recall-Oriented Understudy for Gisting Evaluation) evaluation metric [11]. In this paper, we … Cited by 1 Related articles All 2 versions

A Genetic Based Optimization Model for Extractive Multi-Document Text Summarization HH Saleh, NJ Kadhim, AA Bara’a – researchgate.net … Data source TREC Summary length 200 words Evaluation metrics The proposed method is measured using the Recall-Oriented Understudy for Gisting Evaluation (denoted by evaluation metric) [29]. is considered as the official evaluation metric for text summarization by DUC. … Related articles All 2 versions

Automatic Document Summarization via Deep Neural Networks C Yao, J Shen, G Chen – Computational Intelligence and …, 2015 – ieeexplore.ieee.org … C. Quantitative Analysis 1) Evaluation Metric: This paper adopts a widely used automatic documents summarization evaluation method: Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit[28], which measures quality of peer summary by counting overlapping … Related articles

Text Summarization Using Ant Colony Optimization Algorithm OF HASSAN – 2015 – repository.sustech.edu Page 1. i TEXT SUMMARIZATION USING ANT COLONY OPTIMIZATION ALGORITHM A thesis submitted In Partial Fulfillment of The Requirements For the Degree of Master in Computer Science BY: … Related articles

Study On Text Summarization Using Extractive Methods SM Saleem, R Krithiga, SK Rani, SC Sindhya – ijsetr.org … IEEE Transaction on Knowledge and Data Engineering, Vol. 19, No. 3, pp. 370–383, 2007. [22] Lin Y., “ROUGE: Recall-Oriented Understudy for Gisting Evaluation,” available at: http://www.isi.edu/_cyl/ROUGE/, last visited 2003. Related articles

A framework for multi-document abstractive summarization based on semantic role labelling A Khan, N Salim, YJ Kumar – Applied Soft Computing, 2015 – Elsevier We propose a framework for abstractive summarization of multi-documents, which aims to select contents of summary not from the source document sentences but fro. Cited by 19 Related articles All 5 versions

A multimedia summarizer integrating text and images A d’Acierno, F Gargiulo, V Moscato, A Penta… – … Multimedia Systems and …, 2015 – Springer … 7 Recall-Oriented Understudy for Gisting Evaluation, http://?haydn.?isi.?edu/? ROUGE/?. 8 For brevity, only the first three positions and the last one are shown. Acknowledgments. This research has been partially supported … Cited by 1 Related articles All 4 versions

Summarizing large text collection using topic modeling and clustering based on MapReduce framework NK Nagwani – Journal of Big Data, 2015 – journalofbigdata.springeropen.com … ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation, it includes several measures to quantitatively compare system-generated to human-generated summaries, counting the number of overlapping n-grams of various lengths, word pairs and word sequences … Cited by 9 Related articles All 4 versions

Machine Translationness: a Concept for Machine Translation Evaluation and Detection JM López – 2015 – tdx.cat Page 1. UNIVERSITAT OBERTA DE CATALUNYA Machine Translationness: a Concept for Machine Translation Evaluation and Detection by Joaquim Moré López A thesis submitted in partial fulfillment for the degree of Doctor in Information and Knowledge Society … Related articles

Coreference-based Content Selection for Automatic Summarization of Polish News M Kope? – SELECTED PROBLEMS IN INFORMATION …, 2015 – phd.ipipan.waw.pl … The acronym is expanded as Recall- Oriented Understudy for Gisting Evaluation and covers several metrics: –ROUGEn, which counts n-gram co-occurrences between reference (gold) summaries and system summary, –ROUGE-L, which searches for longest common … Related articles

Swarm Semantic Hybrid Approach for Multi-document Abstractive Summarization A Khan, N Salim, AI Obasa – researchgate.net Page 1. Swarm Semantic Hybrid Approach for Multi- document Abstractive Summarization Atif Khan1, Naomie Salim2, Adekunle Isiaka Obasa3 1,2,3 Faculty of Computing, Universiti Teknologi Malaysia, 81310, Skudai, Johor, Malaysia 1atifkhan@icp.edu.pk … Related articles

Incorporating proximity information in relevance language modeling for extractive speech summarization SH Liu, HS Lee, HT Hung, KY Chen… – … Annual Summit and …, 2015 – ieeexplore.ieee.org Page 1. Incorporating Proximity Information in Relevance Language Modeling for Extractive Speech Summarization Shih-Hung Liu*¥, Hung-Shih Lee*, Hsiao-Tsung Hung†, Kuan-Yu Chen*, Berlin Chen†, Hsin-Min Wang*, Hsu … Related articles All 5 versions

Selecting Social Media Responses to News: A Convex Framework Based On Data Reconstruction Z Chen, L Xu, E Chen, B Chang, Z Wang, Y Li – Proceedings of the 2015 SIAM …, 2015 – SIAM Page 1. Selecting Social Media Responses to News: A Convex Framework Based On Data Reconstruction Zaiyi Chen? Linli Xu? Enhong Chen? Biao Chang? Zhefeng Wang? Yitan Li? Abstract With the explosive growth of … Related articles All 2 versions

Incorporating paragraph embeddings and density peaks clustering for spoken document summarization KY Chen, KW Shih, SH Liu, B Chen… – … (ASRU), 2015 IEEE …, 2015 – ieeexplore.ieee.org Page 1. INCORPORATING PARAGRAPH EMBEDDINGS AND DENSITY PEAKS CLUSTERING FOR SPOKEN DOCUMENT SUMMARIZATION Kuan-Yu Chen*, Kai-Wun Shih#, Shih-Hung Liu*, Berlin Chen#, Hsin-Min Wang* … Cited by 2 Related articles All 2 versions

Extractive Single-Document Summarization Based on Global-Best Harmony Search and a Greedy Local Optimizer M Mendoza, C Cobos, E León – Mexican International Conference on …, 2015 – Springer … Evaluation of the quality of the summaries generated was performed using metrics provided by the assessment tool ROUGE (Recall-Oriented Understudy for Gisting Evaluation) [44] version 1.5.5 (available on internet), which has been widely handled (official metric) by DUC in … Cited by 1 Related articles

A framework for creating natural language descriptions of video streams MUG Khan, N Al Harbi, Y Gotoh – Information Sciences, 2015 – Elsevier This contribution addresses generation of natural language descriptions for important visual content present in video streams. The work starts with implementati. Related articles All 4 versions

Unsupervised document summarization from data reconstruction perspective Z He, C Chen, J Bu, C Wang, L Zhang, D Cai, X He – Neurocomputing, 2015 – Elsevier Due to its wide applications in information retrieval, document summarization is attracting increasing attention in natural language processing. A large body of. Cited by 1 Related articles All 6 versions

The Statement of Originality M Yousefiazar – 2015 – researchonline.mq.edu.au … both extractive and abstractive summarization. The most trusted evaluation metric is Recall-Oriented Understudy for Gisting Evaluation (ROUGE) as a set of automatic metrics and a software package (Lin 2004). This metric counts the overlap units … Related articles All 2 versions

TL; DR: Automatic Summarization With Textual Annotations JS Griggs – cs.cmu.edu Page 1. TL;DR: Automatic Summarization With Textual Annotations Julian S. Griggs 2015 Advised by Ananda Gunawardena Submitted to: Princeton University Department of Computer Science This Thesis represents my own work in accordance with University Regulations … Related articles All 2 versions

Towards an Efficient Approach for Automatic Medical Document Summarization P Gayathri, N Jaisankar – Cybernetics and Information Technologies, 2015 – degruyter.com … the summary. In performance evaluation, the tool Recall- Oriented Understudy for Gisting Evaluation (ROUGE) (http://www.berouge.com) has been used to compute 1-gram score for 100-word summary. The work presented … Related articles All 4 versions

Opinion-aware Information Management: Statistical Summarisation and Knowledge Representation of Opinions. M Bonzanini – 2015 – qmro.qmul.ac.uk Page 1. Opinion-aware Information Management: Statistical Summarisation and Knowledge Representation of Opinions. Bonzanini, Marco The copyright of this thesis rests with the author and no quotation from it or information … Related articles All 3 versions

Summarization of changes in dynamic text collections using Latent Dirichlet Allocation model M Kar, S Nunes, C Ribeiro – Information Processing & Management, 2015 – Elsevier In the area of Information Retrieval, the task of automatic text summarization usually assumes a static underlying collection of documents, disregarding the tem. Cited by 7 Related articles All 3 versions

Summarization of changes in dynamic text collections using Latent Dirichlet Allocation model M Kar, S Nunes, C Ribeiro – Information Processing & Management, 2015 – Elsevier In the area of Information Retrieval, the task of automatic text summarization usually assumes a static underlying collection of documents, disregarding the tem. Cited by 7 Related articles All 3 versions

Twitter Event Summarization Using Phrase Reinforcement Algorithm and NLP Features G Mane, A Kulkarni – International Journal of Advanced …, 2015 – pdfs.semanticscholar.org … Chin-Yew Lin[8] has presented ROUGE: A Package for Automatic Evaluation of Summaries. ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. … ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. … Cited by 1 Related articles

[BOOK] Advances in Artificial Intelligence and Its Applications: 14th Mexican International Conference on Artificial Intelligence, MICAI 2015, Cuernavaca, Morelos, … OP Lagunas, OH Alcántara, GA Figueroa – 2015 – books.google.com Page 1. Obdulia Pichardo Lagunas Oscar Herrera Alcántara Gustavo Arroyo Figueroa (Eds.) Advances in Artificial Intelligence and Its Applications 14th Mexican International Conference on Artificial Intelligence, MICAI 2015 … Related articles All 4 versions

Enhancing extractive summarization with automatic post-processing SMSB Silveira – 2015 – repositorio.ul.pt Page 1. UNIVERSIDADE DE LISBOA FACULDADE DE CIÊNCIAS DEPARTAMENTO DE INFORMÁTICA ENHANCING EXTRACTIVE SUMMARIZATION WITH AUTOMATIC POST-PROCESSING Sara Maria da Silveira Botelho da Silveira Doutoramento em Informática … Related articles All 2 versions

Towards Large Scale Summarization JM Christensen – 2015 – digital.lib.washington.edu … the other automatic methods discussed, blind to linguistic quality. The most popular automatic metric for summary evaluation is ROUGE (Recall-Oriented Understudy for Gisting Evaluation) (Lin, 2004). ROUGE measures n-gram overlap be- … Cited by 1 Related articles All 3 versions

Does summarization help stock prediction? A news impact analysis X Li, H Xie, Y Song, S Zhu, Q Li… – IEEE intelligent …, 2015 – ieeexplore.ieee.org … perspectives that people prioritize for sum- marization quality are readability, relevance, diversity, cover- age, and distortion, which are integrated in the widely used standard summarization evaluation package ROUGE (Recall- Oriented Understudy for Gisting Evaluation)3 and … Cited by 11 Related articles All 7 versions

Automatic broadcast news summarization via rank classifiers and crowdsourced annotation S Parthasarathy, T Hasan – Acoustics, Speech and Signal …, 2015 – ieeexplore.ieee.org … their relative quality [10]. The fact that multiple good summaries can exist is also well known and considered in calculating the ROUGE (Recall-Oriented Understudy for Gisting Evaluation) evaluation metric [11]. In this paper, we … Cited by 1 Related articles All 2 versions

A study on the use of word embeddings and pagerank for vietnamese text summarization V Phung, L De Vine – Proceedings of the 20th Australasian Document …, 2015 – dl.acm.org … The structure of the paper is as follows. Section 2 briefly describes some related works. Section 3 provides an intro- 1ROUGE stands for Recall Oriented Understudy for Gisting Evaluation, see section 5.3 for definition Page 2. … Cited by 2 Related articles All 2 versions

Keyphrase based Evaluation of Automatic Text Summarization F Elghannam, T El-Shishtawy – arXiv preprint arXiv:1505.06228, 2015 – arxiv.org … ROUGE [9] stands for Recall- Oriented Understudy for Gisting Evaluation is a recall measure that counts the number of overlapping n-gram units between the peer summary generated by computer and several reference summaries. … Related articles All 7 versions

SENSEI Coordinator G Riccardi – sensei-conversation.eu … processing PDTB Penn Discourse Treebank PHP PHP Hypertext Preprocessor PNG Portable Network Graphics POS part of speech QA quality assurance REST Representational State Transfer ROUGE Recall-Oriented Understudy for Gisting Evaluation SQL Structured Query … Related articles

A quantitative and qualitative assessment of automatic text summarization systems J Batista, R Ferreira, H Tomaz, R Ferreira… – Proceedings of the …, 2015 – dl.acm.org … The first evaluation is performed by counting the numbers of sentences selected by the system that match the human gold standard. In the second evaluation, the well-know ROUGE (Recall-Oriented Understudy for Gisting Evaluation) [10] is used. … Cited by 4 Related articles

Vertex Cover Algorithm Based Multi-document Summarization Using Information Content of Sentences A John, M Wilscy – Procedia Computer Science, 2015 – Elsevier … For the performance evaluation we used the ROUGUE-1.5.5 (Recall-Oriented Understudy for Gisting Evaluation) package22. … 23. DUC. <http://duc.nist.gov> 24. ROUGE Toolkit. <http://berouge.com/default.aspx> ficial Intelligence Research. 1980. vol.17. p. 35–55 . … Cited by 1 Related articles All 2 versions

Automatic summarization assessment through a combination of semantic and syntactic information for intelligent educational systems A Abdi, N Idris, RM Alguliev, RM Aliguliyev – Information Processing & …, 2015 – Elsevier … redundancy and plagiarism. Lin (2004) proposed an automatic summary assessment system named Recall-Oriented Understudy for Gisting Evaluation, which is used to assess the quality of the summary text. The current system … Cited by 6 Related articles All 7 versions

Overview of the NLPCC 2015 Shared Task: Weibo-Oriented Chinese News Summarization X Wan, J Zhang, S Wen, J Tan – National CCF Conference on Natural …, 2015 – Springer … YTSC-run run1 0.45124 0.29799 0.23561 0.20323 0.28333 run2 0.46747 0.32056 0.25901 0.22655 0.30448 zzubylong run1 0.32441 0.19641 0.13431 0.10510 0.17289 run2 0.36854 0.22465 0.15649 0.12352 0.20000 8 http://berouge.com/ Page 5. … Related articles All 3 versions

Text Summarization Using Particle Swarm Optimization Algorithm ABDEY MAHJOUB – 2015 – repository.sustech.edu … PSO – Particle Swarm Optimization GA – Genetic Algorithm ACO – Ant colony optimization ROUGE – Recall-Oriented Understudy for Gisting Evaluation DUC – Document Understanding Conference AVG-P – Average Precision AVG-R – Average Recall AVG-F – Average F-measure … Related articles

Semi-extractive Multi-document Summarization via Submodular Functions FG Davoodi, Y Chali – … Conference on Statistical Language and Speech …, 2015 – Springer … We use ROUGE (Recall-Oriented Understudy for Gisting Evaluation) [15] package 4 to evaluate the results automatically which is a well-know package for comparing the system generated summaries to a set of reference … ROUGE package is available at http://www.berouge.com … Related articles All 2 versions

Text Summarization Using Latent Semantic Analysis Model in Mobile Android Platform OM Foong, SP Yong, FA Jaid – Modelling Symposium (AMS), …, 2015 – ieeexplore.ieee.org … in the experiment. B. System Performance Evaluation The final output summaries are evaluated using Recall Oriented Understudy for Gisting Evaluation (ROUGE) which is based on Lin [25]. The ROUGE evaluation approach … Related articles

Lcsts: A large scale chinese short text summarization dataset B Hu, Q Chen, F Zhu – arXiv preprint arXiv:1506.05865, 2015 – arxiv.org … As shown in Figure 8, the summary generated by RNN with context by inputing the character-based short text is relatively good, while 6http://www.berouge.com/Pages/default. aspx Figure 8: An example of the generated summaries with UNKs. … Cited by 14 Related articles All 14 versions

Automatic Text Summarization Using Importance of Sentences for Email Corpus S Nadella – 2015 – repository.asu.edu … document. There are two types of evaluation approaches in automatic text summarization. ROGUE (Recall-Oriented Understudy for Gisting Evaluation) is most commonly used evaluation technique. This method relies on recall-based evaluation. The … Related articles All 2 versions

Automatic Text Summarization Using Importance of Sentences for Email Corpus S Nadella – 2015 – repository.asu.edu … document. There are two types of evaluation approaches in automatic text summarization. ROGUE (Recall-Oriented Understudy for Gisting Evaluation) is most commonly used evaluation technique. This method relies on recall-based evaluation. The … Related articles All 2 versions

Automatic summarization of polish news articles by sentence selection K Jassem, ? Pawluczuk – Computer Science and Information …, 2015 – ieeexplore.ieee.org … V. EVALUATION A. Evaluation method ROUGE (DUC conference) ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation [2]. It was introduced by Chin-Yew Lin at Doc- ument Understanding Conference (DUC) in 2004 and since then it has became the standard … Cited by 2 Related articles All 7 versions

Mining Topical Relevant Patterns for Multi-document Summarization Y Wu, Y Gao, Y Li, Y Xu, M Chen – Web Intelligence and …, 2015 – ieeexplore.ieee.org … a big room for the improvement in 2 http://www.berouge.com/Pages/default.aspx 116 Page 4. exploiting pattern-based topic model for document summarization. TABLE I. EXPERIMENTAL RESULTS OF ROUGE EVALUATION … Related articles All 4 versions

Automatic Arabic text summarization: a survey Asma Bader Al-Saleh & Mohamed El B Menai – researchgate.net … position of a perfect method is equal to one. ROUGE14 (Recall-Oriented Understudy for Gisting Evaluation) is a popular and widely used set of automatic evaluation metrics. It consists of a package that automatically eval- uates … Related articles

Learning Sentence Vector Representations to Summarize Yelp Reviews N Khosla, V Venkataraman – 2015 – pdfs.semanticscholar.org … As such, we were forced to look to manual methods to evaluate our methods’ success. The canonical metric used to evaluate automatic summarization is ROUGE, which stands for Recall- Oriented Understudy for Gisting Evaluation. … Related articles All 5 versions

Extractive meeting summarization through speaker zone detection MH Bokaei, H Sameti, YUT Liu – 16th Annual Conference …, 2015 – libtreasures.utdallas.edu … number of the 3The ids of meetings are: ES2004, ES2014, IS1009, TS3003 and TS3007. 4We uses ROUGE package (http://www.berouge.com/) to evaluate our proposed summarization algorithm. 2726 Page 4. Table 1: Results … Cited by 1 Related articles All 2 versions

A Comparative Study Of Hindi Text Summarization Techniques: Genetic Algorithm And Neural Network PG Student, DM COE – 2015 – academicscience.co.in … them. Available evaluation methods are ROUGE (Recall-Oriented Understudy for Gisting Evaluation), intrinsic methods that attempt to measure summary trustfulness by human experts, precision methods and recall methods. … Related articles

AllSummarizer system at MultiLing 2015: Multilingual single and multi-document summarization A Aries, DE Zegour, KW Hidouci – 16th Annual Meeting of the …, 2015 – anthology.aclweb.org … 5.1 Evaluation metrics In “Single document summarization” task, ROUGE (Recall-Oriented Understudy for Gisting Evaluation)(Lin, 2004) is used to evaluate the participated systems. It allows us to evaluate automatic text summaries against human made abstracts. … Related articles All 10 versions

Automatic Enhanced Update Summary Generation System for News Documents SV Kogilavani, CS Kanimozhiselvi… – World Academy of Science, …, 2015 – Citeseer … Manual evaluation can be used, but this is both time and labor intensive as it requires humans to read not only the summaries but also the source documents. One metric used is the Recall- Oriented Understudy for Gisting Evaluation (ROUGE). … Related articles All 4 versions

Paragraph Ranking Based on Eigen Analysis OK Reshma, PCR Raj – Procedia Computer Science, 2015 – Elsevier … evaluated using ROUGE evaluation metric. ROUGE (Recall-Oriented Understudy for Gisting Evaluation) is a set of metrics and a software package used for evaluating automatic summarization. The metric compares an automatically … Related articles All 4 versions

Tell me why: uma arquitetura para fornecer explicações ricas sobre revisões V Woloszyn – 2015 – lume.ufrgs.br … SVD Singular Value Decomposition PCA Principal Component Analysis QA Question Answering ROUGE Recall-Oriented Understudy for Gisting Evaluation KDD Knowledge Discovery in Databases BBN Bayesian Belief Networks DAG Directed Acyclic Graph … Related articles All 2 versions

Abstractive multi-document summarization via phrase selection and merging L Bing, P Li, Y Liao, W Lam, W Guo… – arXiv preprint arXiv: …, 2015 – arxiv.org … 43 and 17. The reason is that System 43 and 17 used category-specific features and trained the feature weights with the category information 3http://www.berouge.com/ Pages/default.aspx in TAC 2010 data. These features help … Cited by 27 Related articles All 11 versions

Extractive Summarization Method for Arabic Text-ESMAT MS Binwahlan – ijcttjournal.org … five human summaries. Summaries of length 50% is created by the proposed method. To evaluate those summaries, ROUGE (Recall-Oriented Understudy for Gisting Evaluation) toolkit [34] is used. ROUGE compares a system … Related articles All 2 versions

Multi-document Arabic Text Summarization KSAL Harazin – 2015 – library.iugaza.edu.ps … realign the rest of units to form a non-redundant sentence. For evaluation, a Recall-Oriented Understudy for Gisting Evaluation ROUGE evaluation measure is used. … R Recall ROUGE Recall-Oriented Understudy for Gisting Evaluation RST Rhetorical Structure Theory … Related articles

Extractive Single-Document Summarization Based on Global-Best Harmony Search and a Greedy Local Optimizer M Mendoza, C Cobos, E León – Mexican International Conference on …, 2015 – Springer … Evaluation of the quality of the summaries generated was performed using metrics provided by the assessment tool ROUGE (Recall-Oriented Understudy for Gisting Evaluation) [44] version 1.5.5 (available on internet), which has been widely handled (official metric) by DUC in … Cited by 1 Related articles

Reader-aware multi-document summarization via sparse coding P Li, L Bing, W Lam, H Li, Y Liao – arXiv preprint arXiv:1504.07324, 2015 – arxiv.org Page 1. arXiv:1504.07324v1 [cs.CL] 28 Apr 2015 Reader-Aware Multi-Document Summarization via Sparse Coding ? Piji Li† Lidong Bing‡ Wai Lam† Hang Li§ and Yi Liao† †Department of Systems Engineering and Engineering … Cited by 10 Related articles All 13 versions

Semantic analysis-enhanced natural language interaction in ubiquitous learning D Wen, Y Gao, G Yang – Ubiquitous Learning Environments and …, 2015 – Springer … The system based on this algorithm has shown the highest performance improvement in a standard Recall-Oriented Understudy for Gisting Evaluation (ROUGE) (Lin 2004) at Document Understand Conference (DUC) 2006 (Vanderwende et al. 2007). … Cited by 1 Related articles All 3 versions

Similarity-Based Query-Focused Multi-document Summarization Using Crowdsourced and Manually-built Lexical-Semantic Resources MA Mohamed, M Oussalah – Trustcom/BigDataSE/ISPA, 2015 …, 2015 – ieeexplore.ieee.org … As for the quantitative evaluation of the systems against baselines and other related state of the art systems, we used Recall Oriented Understudy for Gisting Evaluation (ROUGE) [24], the most widely used official evaluation tool in Text Summarization adopted in all DUC … Cited by 2 Related articles All 4 versions

Leveraging word embeddings for spoken document summarization KY Chen, SH Liu, HM Wang, B Chen… – arXiv preprint arXiv: …, 2015 – arxiv.org Page 1. Leveraging Word Embeddings for Spoken Document Summarization Kuan-Yu Chen*†, Shih-Hung Liu*, Hsin-Min Wang*, Berlin Chen#, Hsin-Hsi Chen† *Institute of Information Science, Academia Sinica, Taiwan #National … Cited by 3 Related articles All 8 versions

Positional language modeling for extractive broadcast news speech summarization. SH Liu, KY Chen, B Chen, HM Wang, HC Yen… – …, 2015 – iis.sinica.edu.tw Page 1. Positional Language Modeling for Extractive Broadcast News Speech Summarization Shih-Hung Liu1, 2, Kuan-Yu Chen1, 2, Berlin Chen3, Hsin-Min Wang1, Hsu-Chun Yen2, Wen-Lian Hsu1 1Institute of Information … Cited by 2 Related articles All 6 versions

On strategies of human multi-document summarization RT Camargo, A Di-Felippo, TAS Pardo – Brazilian Symposium in …, 2015 – producao.usp.br … in the summaries. Regarding informativeness evaluation, we used the traditional automatic ROUGE (Recall-Oriented Understudy for Gisting Evaluation) measure [Lin 2004], which is mandatory in the area. ROUGE computes … Cited by 1 Related articles All 11 versions

Improving Clustering Quality by Automatic Text Summarization M Pourvali, S Orlando, M Gharagozloo – Asia Information Retrieval …, 2015 – Springer Related articles All 2 versions

Using data merging techniques for generating multidocument summarizations D Van Britsom, A Bronselaer… – IEEE Transactions on …, 2015 – ieeexplore.ieee.org Page 1. 576 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 23, NO. 3, JUNE 2015 Using Data Merging Techniques for Generating Multidocument Summarizations Daan Van Britsom, Antoon Bronselaer, and Guy De Tré … Cited by 6 Related articles All 4 versions

Using text mining techniques to extract rationale from existing documentation B Rogers, Y Qiao, J Gung, T Mathur… – Design Computing and …, 2015 – Springer … They achieved an 18.5 % F-value for artifact extraction, a 51.95 % ROUGE-1 (Recall-Oriented Understudy for Gisting Evaluation) F-value for issue summarization, and a 56.15 % ROUGE-1 F-value on solution and reason identification. … Cited by 3 Related articles All 4 versions

Event-based Multi-document Summarization LC dos Santos Marujo – 2015 – lti.cs.cmu.edu … ROUGE — Recall-Oriented Understudy for Gisting Evaluation is the most used summariza- tion evaluation metric. SMO — Sequential Minimal Optimization is an algorithm used to train SVMs. SPER — Spanish Event Reports dataset. SU — Sentence Unit. … Related articles All 6 versions

Semi-extractive multi-document summarization F Ghiyafeh Davoodi – 2015 – uleth.ca Page 1. SEMI-EXTRACTIVE MULTI-DOCUMENT SUMMARIZATION FATEMEH GHIYAFEH DAVOODI Bachelor of Science, Amirkabir University of Technology, Iran, 2008 Master of Science, University of Tehran, 2012 A Thesis … Related articles All 2 versions

Query-based multi-documents summarization using linguistic knowledge and content word expansion A Abdi, N Idris, RM Alguliyev, RM Aliguliyev – Soft Computing, 2015 – Springer Page 1. Soft Comput DOI 10.1007/s00500-015-1881-4 METHODOLOGIES AND APPLICATION Query-based multi-documents summarization using linguistic knowledge and content word expansion Asad Abdi1 · Norisma Idris1 · Rasim M. Alguliyev2 · Ramiz M. Aliguliyev2 … Cited by 3 Related articles All 3 versions

Abstractive microblogs summarization N Uvarova – 2015 – brage.bibsys.no … 9 NIST National Institute of Standards and Technology. 12 NLP Natural Language Processing. 5, 7, 12, 17, 42 PR Phrase Reinforcement. 8 ROUGE Recall-Oriented Understudy for Gisting Evaluation. 12, 17, 25, 27, 40 SCU Summary Content Unit. 13, 14 xiii Page 14. Page 15. … Related articles All 2 versions

Textual opinion summarization based on Cluster_HITS model Y Li, H Feng, W Feng – cmnt.lv … In this model, the upper layer is the extension, including opinion information and review of the helpful * http://www.berouge.com/Pages/default.aspx information, the middle layer is a sentence level, and the bottom is the clustering layer. … Related articles All 2 versions

Swarm intelligence for natural language processing W Al-Saeedan, MEB Menai – International Journal of …, 2015 – inderscienceonline.com Page 1. Int. J. Artificial Intelligence and Soft Computing, Vol. 5, No. 2, 2015 117 Copyright © 2015 Inderscience Enterprises Ltd. Swarm intelligence for natural language processing Wojdan Al-Saeedan and Mohamed El Bachir Menai* … Cited by 2 Related articles All 2 versions

Video summarization by learning submodular mixtures of objectives M Gygli, H Grabner, L Van Gool – Proceedings of the IEEE …, 2015 – cv-foundation.org … We score these and remove the bottom 25%. Finally, we obtain 60 reference summaries (15 per video). In order to predict the interestingness of a segment 4http://www.berouge.com/ 5 Page 6. Short (? 1min 20sec) Long (2min) Method F-measure Recall F-measure Recall … Cited by 32 Related articles All 20 versions

Search engine reinforced semi-supervised classification and graph-based summarization of microblogs Y Chen, X Zhang, Z Li, JP Ng – Neurocomputing, 2015 – Elsevier There is an abundance of information found on microblog services due to their popularity. However the potential of this trove of information is limited by the l. Cited by 9 Related articles All 4 versions

Machine Translationness: a Concept for Machine Translation Evaluation and Detection J Moré i López – 2015 – openaccess.uoc.edu Page 1. UNIVERSITAT OBERTA DE CATALUNYA Machine Translationness: a Concept for Machine Translation Evaluation and Detection by Joaquim Moré López A thesis submitted in partial fulfillment for the degree of Doctor in Information and Knowledge Society … Cited by 1 Related articles

Word Graph-Based Multi-sentence Compression: Re-ranking Candidates Using Frequent Words AV Luong, NT Tran, VG Ung… – Knowledge and Systems …, 2015 – ieeexplore.ieee.org … Word Synonym is used to increase node mapping 6http://www.mturk.com 7We use the ROUGE-1.5.5 available from http://www.berouge.com 8Source code of two baselines are pre-implemented by Boudin and Morin [9] and are available for download. … Related articles

Automated generation of movie tributes AMS Aparício – 2015 – repositorio.iscte.pt Page 1. University Institute of Lisbon Department of Information Science and Technology Automated Generation of Movie Tributes Ana Marta Simões Aparício A Dissertation presented in partial fulfillment of the Requirements for the Degree of Master in Computer Science … Related articles All 3 versions

Combination of features for vietnamese news multi-document summarization VG Ung, AV Luong, NT Tran… – Knowledge and Systems …, 2015 – ieeexplore.ieee.org … 4See http://www.wikinews.org 5Recall-Oriented Understudy for Gisting Evaluation. The ROUGE-1.5.5 is available at http://www.berouge.com 190 Page 6. TABLE III. EVALUATION RESULTS OF VIETNAMESEMDS DATA ROUGE-1 ROUGE-2 ROUGE-SU4 … Cited by 1 Related articles

Automatic Text Summarization Š Hlavá? – 2015 – dspace.cvut.cz … In most cases, those user-written summaries are then by some metric (for example ROUGE, [19]) compared with system-generated summaries. In most articles that were analysed, evaluation is done by ROUGE or Recall-Oriented Understudy for Gisting Evaluation. … Related articles

Data-driven approaches to content selection for data-to-text generation D Gkatzia – 2015 – ros.hw.ac.uk Page 1. DATA-DRIVEN APPROACHES TO CONTENT SELECTION FOR DATA-TO-TEXT GENERATION by Dimitra Gkatzia Submitted for the degree of Doctor of Philosophy Department of Computer Science School of Mathematical and Computer Sciences … Cited by 1 Related articles All 2 versions

Automatic machine translation evaluation: A Qualitative Approach EC Pujadas – 2015 – tdx.cat Page 1. Automatic Machine Translation Evaluation: A Qualitative Approach Elisabet Comelles Pujadas ADVERTIMENT. La consulta d’aquesta tesi queda condicionada a l’acceptació de les següents condicions d’ús: La difusió … All 2 versions

A solution to extractive summarization based on document type and a new measure for sentence similarity RFL MELLO – 2015 – repositorio.ufpe.br Page 1. A SOLUTION TO EXTRACTIVE SUMMARIZATION BASED ON DOCUMENT TYPE AND A NEW MEASURE FOR SENTENCE SIMILARITY Por Rafael Ferreira Leite de Mello Ph.D. Thesis Universidade Federal de Pernambuco … Related articles

Helpfulness Guided Review Summarization W Xiong – 2015 – d-scholarship.pitt.edu Page 1. HELPFULNESS-GUIDED REVIEW SUMMARIZATION by Wenting Xiong BE in Information Engineering, Beijing University of Posts and Telecommunications, 2008 Submitted to the Graduate Faculty of the Kenneth P. Dietrich School of Arts and Sciences, … Cited by 1 Related articles All 12 versions