DOCSLIB.ORG

Abstractive Multi-Document Summarization with Semantic Infor- Mation Extraction

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Abstractive Multi-Document Summarization with Semantic Infor- Mation Extraction Abstractive Multi-document Summarization with Semantic Infor- mation Extraction Wei Li Key Lab of Intelligent Info. Processing, Institute of Computing Technology, CAS Beijing, 100190, China [email protected] analysis without semantic analysis and abstract Abstract representation. Fully abstractive summarization approach re- This paper proposes a novel approach to quires a separate process for the analysis of texts generate abstractive summary for multi- that serves as an intermediate step before the ple documents by extracting semantic in- generation of sentences (Genest and Lapalme, formation from texts. The concept of 2011). Statistics of words or phrases and syntac- Basic Semantic Unit (BSU) is defined to tical analysis that have been widely used in exist- describe the semantics of an event or ac- ing summarization approaches are all shallow tion. A semantic link network on BSUs is processing of text. It is necessary to explore constructed to capture the semantic in- summarization methods based on deeper seman- formation of texts. Summary structure is tic analysis. planned with sentences generated based We define the concept of Basic Semantic Unit on the semantic link network. Experi- (BSU) to express the semantics of texts. A BSU ments demonstrate that the approach is is an action indicator with its obligatory argu- effective in generating informative, co- ments which contain actor and receiver of the herent and compact summary. action. BSU is the most basic element of coher- ent information in texts, which can describe the 1 Introduction semantics of an event or action. The semantic information of texts is represented by extracting Most automatic summarization approaches are BSUs and constructing BSU semantic link net- extractive which leverage only literal or syntactic work (Zhuge, 2009). Semantic Link Network information in documents. Sentences are extract- consists of semantic nodes, semantic links and ed from the original documents directly by rank- reasoning rules (Zhuge, 2010; 2011; 2012; ing or scoring and only little post-editing is made 2015b). The semantic nodes can be any resources. (Yih et al., 2007; Wan et al., 2007; Wang et al., In this work, the semantic nodes are BSUs ex- 2008; Wan and Xiao, 2009). Pure extraction has tracted from texts. We use semantic relatedness intrinsic limits compared to abstraction (Carenini between BSUs as semantic links. Then summary and Cheung, 2008). can be generated based on the semantic link net- Abstractive summarization requires semantic work through summary structure planning. analysis and abstract representation of texts, The characteristics of our approaches are as which need knowledge on and beyond the texts follows: (Zhuge, 2015a). There are some abstractive ap- Each BSU describes the semantics of an proaches in recent years: sentence compression event or action. The semantic relatedness be- (Knight and Marcu, 2000; Knight and Marcu, tween BSUs can capture the context seman- 2002; Cohn and Lapata, 2009), sentence fusion tic relations of texts. (Barzilay and McKeown, 2005; Filippova and The BSU semantic link network is an ab- Strube, 2008), and sentence revision (Tanaka et stract representation of texts. Reduction on al., 2009). However, these approaches are sen- the network can obtain important infor- tence rewriting techniques based on syntactical mation of texts with no redundancy. 1908 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1908–1913, Lisbon, Portugal, 17-21 September 2015. c 2015 Association for Computational Linguistics. Summary is built from sentence to sentence 2011). They extract binary relations from the to a coherent body of information based on web, which is different from our approach that the BSU semantic link network by summary extracts events or actions expressed in texts. structure planning. 3 The Summarization Framework 2 Related Work Our system produces an abstractive summary for There are some abstractive summarization ap- a set of topic related documents. It consists of proaches in recent years. An approach TTG at- two major components: Information extraction tempts to generate abstractive summary by using and summary generation. text-to-text generation to generate sentence for each subject-verb-object triple (Genest and 3.1 Information Extraction Lapalme, 2011). A system that attempts to gen- The semantic information of texts is obtained by erate abstractive summaries for spoken meetings extracting BSUs and constructing BSU semantic was proposed (Wang and Cardie, 2013). It iden- link network. A BSU is represented as an actor- tifies relation instances that are represented by a action-receiver triple, which can both detects lexical indicator with an argument constituent the crucial content and incorporates enough syn- from texts. Then the relation instances are filled tactic information to facilitate the downstream into templates which are extracted by applying sentence generation. Some actions may not have multiple sequence alignment. Both of these sys- the receiver argument. For example, “Flight tems need to select a subset of the large volumes MH370 – disappear” and “Flight MH370 - leave of generated sentences. However, our system - Kuala Lumpur” are two BSUs. generates summary directly by summary struc- BSU Extraction. BSUs are extracted from the ture planning. It can generate well-organized and sentences of the documents. The texts are pre- coherent summary more effectively. processed by name entity recognition (Finkel et A recent work aims to generate abstractive al., 2005) and co-reference resolution (Lee et al., summary based on Abstract Meaning Represen- 2011). Constituent and dependency parses are tation (AMR) (Liu et al., 2015). It first parses the obtained by Stanford parser (Klein and Manning, source text into AMR graphs, and then trans- 2003). The eligible action indicator is restricted forms them into a summary graph and plans to to be a predicate verb; the eligible actor and re- generate text from it. This work only focuses on ceiver arguments are noun phrase. Both the actor the graph-to-graph transformation. The module and receiver arguments take the form of constit- of text generation from AMR has not been de- uents in the parse tree. A valid BSU should have veloped. The nodes and edges of AMR graph are one action indicator and at least one actor argu- entities and relations between entities respective- ment, and satisfy the following constraints: ly, which are sufficiently different from the BSUs The actor argument is the nominal subject or semantic link network. Moreover, texts can be external subject or the complement of a pas- generated efficiently from the BSUs network. sive verb which is introduced by the preposi- Another recent abstractive summarization meth- tion “by” and does the action. od generates new sentences by selecting and The receiver argument is the direct object or merging phrases from the input documents (Bing the passive nominal subject or the object of et al., 2015). It first extracts noun phrases and a preposition following the action verb. verb-object phrases from the input documents, We create some manual rules and syntactic and then calculates saliency scores for them. An constraints to identify all BSUs based on the syn- ILP optimization framework is used to simulta- tactic structure of sentences in the input texts. neously select and merge informative phrases to maximize the salience of phrases and meanwhile Constructing BSU Semantic Link Network. satisfy the sentence construction constraints. As The semantic relatedness between BSUs contains the results show that the method is difficult to three parts: Arguments Semantic Relatedness generate new informative sentences really differ- (ASR), Action-Verbs Semantic Relatedness ent from the original sentences and may generate (VSR) and Co-occurrence in the Same Sentence some none factual sentences since phrases from (CSS). Arguments of BSUs include actors and different sentences are merged. receivers, which both are noun phrases and indi- Open information extraction has been pro- cate concepts or entities in the text. When com- posed by (Banko et al., 2007; Etzioni et al., puting ASR, the semantic relatedness between concepts must be measured. We use the explicit 1909 semantic analysis based on Wikipedia to com- Basic Features Number of words in actor/receiver pute semantic relatedness between concepts (Ga- Number of nouns in actor/receiver brilovich and Markovitch, 2007). When compu- Number of new nouns in actor/receiver Actor/receiver has capitalized word? ting VSR, WordNet-based measure is used to Actor/receiver has stopword? calculate the semantic relatedness between action Action is a phrasal verb? Content Features verbs (Mihalcea et al., 2006). CSS is measured Actor/receiver has name entity? TF/IDF/TF-IDF of action whether two different BSUs co-occur in the same TF/IDF/TF-IDF min max average of actor/receiver sentence. Semantic relations between BSUs are Syntax Features Constituent tag of actor/action/receiver computed by linearly combining these three parts. Dependency relation of action with actor Then BSUs that are extracted from the texts form Dependency relation of action with receiver a semantic link network. Table 1. Features for BSU summary-worthy Semantic Link Network Reduction. A dis- scoring. We use SVM-light with RBF kernel criminative ranker based on Support Vector Re- by default parameters (Joachims, 1999). gression (SVR) (Smola and Scholkopf, 2004) is utilized to assign
Load more

Recommended publications
  • Automatic Summarization of Student Course Feedback
    Automatic Summarization of Student Course Feedback Wencan Luo† Fei Liu‡ Zitao Liu† Diane Litman† †University of Pittsburgh, Pittsburgh, PA 15260 ‡University of Central Florida, Orlando, FL 32716 wencan, ztliu, litman @cs.pitt.edu [email protected] { } Abstract Prompt Describe what you found most interesting in today’s class Student course feedback is generated daily in Student Responses both classrooms and online course discussion S1: The main topics of this course seem interesting and forums. Traditionally, instructors manually correspond with my major (Chemical engineering) analyze these responses in a costly manner. In S2: I found the group activity most interesting this work, we propose a new approach to sum- S3: Process that make materials marizing student course feedback based on S4: I found the properties of bike elements to be most the integer linear programming (ILP) frame- interesting work. Our approach allows different student S5: How materials are manufactured S6: Finding out what we will learn in this class was responses to share co-occurrence statistics and interesting to me alleviates sparsity issues. Experimental results S7: The activity with the bicycle parts on a student feedback corpus show that our S8: “part of a bike” activity approach outperforms a range of baselines in ... (rest omitted, 53 responses in total.) terms of both ROUGE scores and human eval- uation. Reference Summary - group activity of analyzing bicycle’s parts - materials processing - the main topic of this course 1 Introduction Table 1: Example student responses and a reference summary Instructors love to solicit feedback from students. created by the teaching assistant. ‘S1’–‘S8’ are student IDs.
    [Show full text]
  • Using N-Grams to Understand the Nature of Summaries
    Using N-Grams to Understand the Nature of Summaries Michele Banko and Lucy Vanderwende One Microsoft Way Redmond, WA 98052 {mbanko, lucyv}@microsoft.com views of the event being described over different Abstract documents, or present a high-level view of an event that is not explicitly reflected in any single document. A Although single-document summarization is a useful multi-document summary may also indicate the well-studied task, the nature of multi- presence of new or distinct information contained within document summarization is only beginning to a set of documents describing the same topic (McKeown be studied in detail. While close attention has et. al., 1999, Mani and Bloedorn, 1999). To meet these been paid to what technologies are necessary expectations, a multi-document summary is required to when moving from single to multi-document generalize, condense and merge information coming summarization, the properties of human- from multiple sources. written multi-document summaries have not Although single-document summarization is a well- been quantified. In this paper, we empirically studied task (see Mani and Maybury, 1999 for an characterize human-written summaries overview), multi-document summarization is only provided in a widely used summarization recently being studied closely (Marcu & Gerber 2001). corpus by attempting to answer the questions: While close attention has been paid to multi-document Can multi-document summaries that are summarization technologies (Barzilay et al. 2002, written by humans be characterized as Goldstein et al 2000), the inherent properties of human- extractive or generative? Are multi-document written multi-document summaries have not yet been summaries less extractive than single- quantified.
    [Show full text]
  • Automatic Summarization of Medical Conversations, a Review Jessica Lopez
    Automatic summarization of medical conversations, a review Jessica Lopez To cite this version: Jessica Lopez. Automatic summarization of medical conversations, a review. TALN-RECITAL 2019- PFIA 2019, Jul 2019, Toulouse, France. pp.487-498. hal-02611210 HAL Id: hal-02611210 https://hal.archives-ouvertes.fr/hal-02611210 Submitted on 30 May 2020 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Jessica López Espejel Automatic summarization of medical conversations, a review Jessica López Espejel 1, 2 (1) CEA, LIST, DIASI, F-91191 Gif-sur-Yvette, France. (2) Paris 13 University, LIPN, 93430 Villateneuse, France. [email protected] RÉSUMÉ L’analyse de la conversation joue un rôle important dans le développement d’appareils de simulation pour la formation des professionnels de la santé (médecins, infirmières). Notre objectif est de développer une méthode de synthèse automatique originale pour les conversations médicales entre un patient et un professionnel de la santé, basée sur les avancées récentes en matière de synthèse à l’aide de réseaux de neurones convolutionnels et récurrents. La méthode proposée doit être adaptée aux problèmes spécifiques liés à la synthèse des dialogues. Cet article présente une revue des différentes méthodes pour les résumés par extraction et par abstraction et pour l’analyse du dialogue.
    [Show full text]
  • Exploring Sentence Vector Spaces Through Automatic Summarization
    Under review as a conference paper at ICLR 2018 EXPLORING SENTENCE VECTOR SPACES THROUGH AUTOMATIC SUMMARIZATION Anonymous authors Paper under double-blind review ABSTRACT Vector semantics, especially sentence vectors, have recently been used success- fully in many areas of natural language processing. However, relatively little work has explored the internal structure and properties of spaces of sentence vectors. In this paper, we will explore the properties of sentence vectors by studying a par- ticular real-world application: Automatic Summarization. In particular, we show that cosine similarity between sentence vectors and document vectors is strongly correlated with sentence importance and that vector semantics can identify and correct gaps between the sentences chosen so far and the document. In addition, we identify specific dimensions which are linked to effective summaries. To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties. We also compare the features of differ- ent methods of sentence embeddings. Many of these insights have applications in uses of sentence embeddings far beyond summarization. 1 INTRODUCTION Vector semantics have been growing in popularity for many other natural language processing appli- cations. Vector semantics attempt to represent words as vectors in a high-dimensional space, where vectors which are close to each other have similar meanings. Various models of vector semantics have been proposed, such as LSA (Landauer & Dumais, 1997), word2vec (Mikolov et al., 2013), and GLOVE(Pennington et al., 2014), and these models have proved to be successful in other natural language processing applications. While these models work well for individual words, producing equivalent vectors for sentences or documents has proven to be more difficult.
    [Show full text]
  • Keyphrase Based Evaluation of Automatic Text Summarization
    International Journal of Computer Applications (0975 – 8887) Volume 117 – No. 7, May 2015 Keyphrase based Evaluation of Automatic Text Summarization Fatma Elghannam Tarek El-Shishtawy Electronics Research Institute Faculty of Computers and Information Cairo, Egypt Benha University, Benha, Egypt ABSTRACT KpEval idea is to count the matches between the peer The development of methods to deal with the informative summary and reference summaries for the essential parts of contents of the text units in the matching process is a major the summary text. KpEval have three main modules, i) challenge in automatic summary evaluation systems that use lemma extractor module that breaks the text into words and fixed n-gram matching. The limitation causes inaccurate extracts their lemma forms and the associated lexical and matching between units in a peer and reference summaries. syntactic features, ii) keyphrase extractor that extracts The present study introduces a new Keyphrase based important keyphrases in their lemma forms, and iii) the Summary Evaluator (KpEval) for evaluating automatic evaluator that scoring the summary based on counting the summaries. The KpEval relies on the keyphrases since they matched keyphrases occur between the peer summary and one convey the most important concepts of a text. In the or more reference summaries. The remaining of this paper is evaluation process, the keyphrases are used in their lemma organized as follows: Section 2 reviews the previous works; form as the matching text unit. The system was applied to Section 3 the proposed keyphrase based summary evaluator; evaluate different summaries of Arabic multi-document data Section 4 discusses the performance evaluation; and section 5 set presented at TAC2011.
    [Show full text]
  • Latent Semantic Analysis and the Construction of Coherent Extracts
    Latent Semantic Analysis and the Construction of Coherent Extracts Tristan Miller German Research Center for Artificial Intelligence0 Erwin-Schrodinger-Straße¨ 57, D-67663 Kaiserslautern [email protected] Keywords: automatic summarization, latent semantic analy- many of these techniques are tied to a particular sis, LSA, coherence, extracts language or require resources such as a list of dis- Abstract course keywords and a manually marked-up cor- pus; others are constrained in the type of summary We describe a language-neutral au- they can generate (e.g., general-purpose vs. query- tomatic summarization system which focussed). aims to produce coherent extracts. It In this paper, we present a new, recursive builds an initial extract composed solely method for automatic text summarization which of topic sentences, and then recursively aims to preserve both the topic coverage and fills in the topical lacunae by provid- the coherence of the source document, yet has ing linking material between semanti- minimal reliance on language-specific NLP tools. cally dissimilar sentences. While exper- Only word- and sentence-boundary detection rou- iments with human judges did not prove tines are required. The system produces general- a statistically significant increase in tex- purpose extracts of single documents, though it tual coherence with the use of a latent should not be difficult to adapt the technique semantic analysis module, we found a to query-focussed summarization, and may also strong positive correlation between co- be of use in improving the coherence of multi- herence and overall summary quality. document summaries. 2 Latent semantic analysis 1 Introduction Our system fits within the general category of IR- A major problem with automatically-produced based systems, but rather than comparing text with summaries in general, and extracts in particular, the standard vector-space model, we employ la- is that the output text often lacks fluency and orga- tent semantic analysis (LSA) [Deerwester et al., nization.
    [Show full text]
  • Leveraging Word Embeddings for Spoken Document Summarization
    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 Taiwan Normal University, Taiwan †National Taiwan University, Taiwan * # † {kychen, journey, whm}@iis.sinica.edu.tw, [email protected], [email protected] Abstract without human annotations involved. Popular methods include Owing to the rapidly growing multimedia content available on the vector space model (VSM) [9], the latent semantic analysis the Internet, extractive spoken document summarization, with (LSA) method [9], the Markov random walk (MRW) method the purpose of automatically selecting a set of representative [10], the maximum marginal relevance (MMR) method [11], sentences from a spoken document to concisely express the the sentence significant score method [12], the unigram most important theme of the document, has been an active area language model-based (ULM) method [4], the LexRank of research and experimentation. On the other hand, word method [13], the submodularity-based method [14], and the embedding has emerged as a newly favorite research subject integer linear programming (ILP) method [15]. Statistical because of its excellent performance in many natural language features may include the term (word) frequency, linguistic processing (NLP)-related tasks. However, as far as we are score, recognition confidence measure, and prosodic aware, there are relatively few studies investigating its use in information. In contrast, supervised sentence classification extractive text or speech summarization. A common thread of methods, such as the Gaussian mixture model (GMM) [9], the leveraging word embeddings in the summarization process is Bayesian classifier (BC) [16], the support vector machine to represent the document (or sentence) by averaging the word (SVM) [17], and the conditional random fields (CRFs) [18], embeddings of the words occurring in the document (or usually formulate sentence selection as a binary classification sentence).
    [Show full text]
  • Automatic Summarization and Readability
    COGNITIVE SCIENCE MASTER THESIS Automatic summarization and Readability LIU-IDA/KOGVET-A–11/004–SE Author: Supervisor: Christian SMITH Arne JONSSON¨ [email protected] [email protected] List of Figures 2.1 A simplified graph where sentences are linked and weighted ac- cording to the cosine values between them. 10 3.1 Evaluation of summaries on different dimensionalities. The X-axis denotes different dimensionalities, the Y-axis plots the mean value from evaluations on several seeds on each dimensionality. 18 3.2 The iterations of PageRank. The figure depicts the ranks of the sentences plotted on the Y-axis and the iterations on the X-axis. Each series represents a sentence. 19 3.3 The iterations of PageRank in different dimensionalities of the RI- space. The figure depicts 4 different graphs, each representing the trial of a specific setting of the dimensionality. From the left the dimensionalities of 10, 100, 300 and 1000 were used. The ranks of the sentences is plotted on the Y-axis and the iterations on the X-axis. Each series represents a sentence. 20 3.4 Figures of sentence ranks on different damping factors in PageRank 21 3.5 Effect of randomness, same text and settings on ten different ran- dom seeds. The final ranks of the sentences is plotted on the Y, with the different seeds on X. The graph depicts 9 trials at follow- ing dimensionalities, from left: 10, 20, 50, 100, 300, 500, 1000, 2000, 10000. 22 3.6 Values sometimes don’t converge on smaller texts. The left graph depicts the text in d=100 and the right graph d=20.
    [Show full text]
  • Question-Based Text Summarization
    View metadata, citation and similar papers at core.ac.uk brought to you by CORE provided by Drexel Libraries E-Repository and Archives Question-based Text Summarization A Thesis Submitted to the Faculty of Drexel University by Mengwen Liu in partial fulfillment of the requirements for the degree of Doctor of Philosophy December 2017 c Copyright 2017 Mengwen Liu. All Rights Reserved. ii Dedications This thesis is dedicated to my family iii Acknowledgments I would like to thank to my advisor, Prof. Xiaohua Tony Hu for his generous guidance and support in the past five and a half years. Prof. Hu provided a flexible environment for me to explore different research fields. He encouraged me to work with intellectual peers and attend professional activities, and gave immediate suggestions on my studies and career development. I am also grateful to Prof. Yuan An, whom I worked closely in the first two years of my doctoral study. I thank to him for offering guidance about research, paper review, collaboration with professionals from other fields, and scientific writings. I would like to thank my dissertation committee of Prof. Weimao Ke, Prof. Erjia Yan, Prof. Bei Yu, and Prof. Yi Fang. Prof. Ke provided many suggestions towards my research projects that relate to information retrieval and my thesis topic. Prof. Yan offered me lots of valuable suggestions for my prospectus and thesis and encouraged me to conduct long-term research. Prof. Yu inspired my interest in natural language processing and text mining, and taught me how to do research from scratch with great patience.
    [Show full text]
  • Automatic Text Summarization: Past, Present and Future Horacio Saggion, Thierry Poibeau
    Automatic Text Summarization: Past, Present and Future Horacio Saggion, Thierry Poibeau To cite this version: Horacio Saggion, Thierry Poibeau. Automatic Text Summarization: Past, Present and Future. T. Poibeau; H. Saggion. J. Piskorski, R. Yangarber. Multi-source, Multilingual Information Extraction and Summarization, Springer, pp.3-13, 2012, Theory and Applications of Natural Language Process- ing, 978-3-642-28569-1. hal-00782442 HAL Id: hal-00782442 https://hal.archives-ouvertes.fr/hal-00782442 Submitted on 27 Jul 2016 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Chapter 1 Automatic Text Summarization: Past, Present and Future Horacio Saggion and Thierry Poibeau Abstract Automatic text summarization, the computer-based production of con- densed versions of documents, is an important technology for the information soci- ety. Without summaries it would be practically impossible for human beings to get access to the ever growing mass of information available online. Although research in text summarization is over fifty years old, some efforts are still needed given the insufficient quality of automatic summaries and the number of interesting summa- rization topics being proposed in different contexts by end users (“domain-specific summaries”, “opinion-oriented summaries”, “update summaries”, etc.).
    [Show full text]
  • Automatic Text Summarization: a Review
    eKNOW 2017 : The Ninth International Conference on Information, Process, and Knowledge Management Automatic Text Summarization: A review Naima Zerari, Samia Aitouche, Mohamed Djamel Mouss, Asma Yaha Automation and Manufacturing Laboratory Department of Industrial Engineering Batna 2 University Batna, Algeria Email: [email protected], [email protected], [email protected], [email protected] Abstract—As we move into the 21st century, with very rapid that the user wants to get [4]. With document summary mobile communication and access to vast stores of information, available, users can easily decide its relevancy to their we seem to be surrounded by more and more information, with interests and acquire desired documents with much less less and less time or ability to digest it. The creation of the mental loads involved. [5]. automatic summarization was really a genius human solution to solve this complicated problem. However, the application of Furthermore, the goal of automatic text summarization is this solution was too complex. In reality, there are many to condense the documents into a shorter version and problems that need to be addressed before the promises of preserve important contents [3]. Text Summarization automatic text summarization can be fully realized. Basically, methods can be classified into two major methods extractive it is necessary to understand how humans summarize the text and abstractive summarization [6]. and then build the system based on that. Yet, individuals are so The rest of the paper is organized as follows: Section 2 is different in their thinking and interpretation that it is hard to about text summarization, precisely the definition of the create "gold-standard" summary against which output summaries will be evaluated.
    [Show full text]
  • An Automatic Text Summarization: a Systematic Review
    EasyChair Preprint № 869 An Automatic Text Summarization: A Systematic Review Vishwa Patel and Nasseh Tabrizi EasyChair preprints are intended for rapid dissemination of research results and are integrated with the rest of EasyChair. March 31, 2019 An Automatic Text Summarization: A Systematic Review Vishwa Patel1;2 and Nasseh Tabrizi1;3 1 East Carolina University, Greenville NC 27858, USA 2 [email protected] 3 [email protected] Abstract. The 21st century has become a century of information over- load, where in fact information related to even one topic (due to its huge volume) takes a lot of time to manually summarize it into few lines. Thus, in order to address this problem, Automatic Text Summarization meth- ods have been developed. Generally, there are two approaches that are currently being used in practice: Extractive and Abstractive methods. In this paper, we have reviewed papers from IEEE and ACM libraries those related to Automatic Text Summarization for the English language. Keywords: Automatic Text Summarization · Extractive · Abstractive · Review paper 1 Introduction Nowadays, the Internet has become one of the important sources of information. We surf the Internet, to find some information related to a certain topic. But search engines often return an excessive amount of information for the end user to read increasing the need for Automatic Text Summarization(ATS), increased in this modern era. The ATS will not only save time but also provide important insight into a piece of information. Many years ago scientists started working on ATS but the peak of interest in it started from the year 2000. In the early 21st century, new technologies emerged in the field of Natural Language Processing (NLP) to enhance the capabilities of ATS.
    [Show full text]