Text Summarization

The study investigates the influence of summary writing in an FL on the development of students' EFL reading skills. Eighty university students participated in a six-month long quasi-experimental study. They were divided into an experimental and a control group, both of which followed the same syllabus and read the same texts. The difference between them was that the experimental group regularly wrote summaries of the texts they had read while the control group engaged in typical FCE reading tasks: multiple choice questions, true/false statements and matching. The development of students' reading skills was measured by assessing their level of comprehension before and after an EFL course involving summary writing. The study showed a statistically significant difference in the reading skills of the two groups suggesting that summarising has a positive influence on reading development. Progress in students' reading skills did not correlate with the quality of the summaries they wrote. Summary writing was shown to be highly beneficial for weaker readers. The results of the study might assist in the search for effective techniques for developing text comprehension in the FL classroom.

During maintenance developers cannot read the entire code of large systems. They need a way to get a quick understanding of source code entities (such as, classes, methods, packages, etc.), so they can efficiently identify and then focus on the ones related to their task at hand. Sometimes reading just a method header or a class name does not tell enough about its purpose and meaning, while reading the entire implementation takes too long. We study a solution which mitigates the two approaches, i.e., short and accurate textual descriptions that illustrate the software entities without having to read the details of the implementation. We create such descriptions using techniques from automatic text summarization. The paper presents a study that investigates the suitability of various such techniques for generating source code summaries. The results indicate that a combination of text summarization techniques is most appropriate for source code summarization and that developers generally agree with the summaries produced.

Text summarization is the process of shortening the source document into condensed form keeps overall idea about the document. The techniques of text summarization are abstractive and extractive. The abstractive summarization requires natural language processing tools for summarizing the documents. The extractive summarization requires statistical, linguistics and heuristics methods for ranking the sentences. Many techniques have been developed for summarization of text in various languages. This paper discuss about the methods of abstractive and extractive text summarization and its merits and de-merits. The study also shows that the extractive methods are easy to implement and give better result in summarization within short span of time.

Abstrak Perkembangan dokumen teks khususnya melalui melalui media Internet membuat jumlah dokumen menjadi sangat banyak dan menyebabkan pencarian didalam dokumen berbasis teks menjadi sebuah pekerjaan yang tidak mudah. Penggalian informasi yang terkandung dalam suatu dokumen teks tersebut diperlukan untuk membangkitkan informasi yang mencakup keseluruhan dokumen secara ringkas yang disebut peringkasan. Peringkasan teks dilakukan dengan cara memberika bobot pada setiap kalimat dengan menggunakan algoritma TF*IDF dan Inverted Index. Tahapan yang dilakukan yaitu preprocessing, tokenizing, filtering & stemming. Dari hasil percobaan dihasilkan dokumen yang berhasil diringkas. Data yang digunakan berjumlah 5 dokumen yang menghasilkan rata-rata tingkat peringkasannya 67.44%, sehingga peringkasan yang ada dapat digunakan sebagai sarana untuk membantu meringkas dokumen teks yang ada. Penelitian selanjutnya diharapkan dapat ditingkatkan dengan adanya fasilitas untuk meningkatkan ataupun menurunkan tingkat ringkasannya sehingga dapat diatur sesuai keinginan.

Due to the explosive growth of the world-wide web, automatic text summarization has become an essential tool for web users. In this paper we present a novel approach for creating text summaries. Using fuzzy logic and word-net, our model extracts the most relevant sentences from an original document. The approach utilizes fuzzy measures and inference on the extracted textual information from the document to find the most significant sentences. Experimental results reveal that the proposed approach extracts the most relevant sentences when compared to other commercially available text summarizers. Text pre-processing based on word-net and fuzzy analysis is the main part of our work.

A summary of a document is a (much) shorter text conveys the most important information from the source document. Summary of the text must contain important information from the document. Summary of the text can be generated from a single document or from multiple documents. In single-document summarization, the summary of only one document is to be built, while in multi-document summarization the summary of a whole collection of documents (such as all today’s news or all search results for a query) is built. In this paper authors have represented review on single-document summaries for the text data written in the various Languages. This paper also presents detection and removal of Deadwood, Extractive and Abstractive summarization methods for Punjabi language. An Extractive summarization method only decides, for each sentence, whether or not it will be included in the summary. An Abstractive summarization  process consists of “understanding” the original text and “re-telling” it in fewer words

A most prominent phenomenon of natural lan-guages is variability-stating the same meaning in various ways. Robust language processing applica-tions-like Information Retrieval (IR), Question Answering (QA), Information Extraction (IE), text summarization and machine translation-must recognize the different forms in which their inputs and requested outputs might be expressed. Today, inferences about language variability are often per-formed by practical systems at a

The TIPSTER Text Summarization Evaluation (SUMMAC) has developed several new extrinsic and intrinsic methods for evaluating summaries. It has established definitively that automatic text summarization is very effective in relevance assessment tasks on news articles. Summaries as short as 17% of full text length sped up decision-making by almost a factor of 2 with no statistically significant degradation in accuracy. Analysis of feedback forms filled in after each decision indicated that the intelligibility of present-day machine-generated summaries is high. Systems that performed most accurately in the production of indicative and informative topic-related summaries used term frequency and co-occurrence statistics, and vocabulary overlap comparisons between text passages. However, in the absence of a topic, these statistical methods do not appear to provide any additional leverage: in the case of generic summaries, the systems were indistinguishable in accuracy. The paper discusses some of the tradeoffs and challenges faced by the evaluation, and also lists some of the lessons learned, impacts, and possible future directions. The evaluation methods used in the SUMMAC evaluation are of interest to both summarization evaluation as well as evaluation of other 'output-related' NLP technologies, where there may be many potentially acceptable outputs, with no automatic way to compare them.

Text Summarization is an area of research that has been studied extensively for the last half – century. This work discusses text summarization in detail and covers research into the field of text summarization from the early approaches which included mostly machine learning methods to summarization tools and newly proposed algorithms.
This project also involved the implementation of an extractive text summarizer using one of the unsupervised techniques, employing graph theory’s Weighted Undirected Graph and implementing the PageRank algorithm for sentence and word ranking. Implementation was carried out using C# programming language.

Okuduğunu anlamanın en önemli göstergelerinden birisi okunan metni sözlü veya yazılı olarak özetleyebilmektir. Özetleme; bir metinde işlenen konu ve ana düşünceyi destekleyen temel yargıların özünü sözlü veya yazılı anlatabilme becerisi olarak tanımlanabilir. Bu araştırmada, ortaokul 6, 7 ve 8. sınıf öğrencilerinin bilgilendirici ve öyküleyici metinleri özetleme becerileri incelenmiştir. Araştırmaya Sakarya ili Akyazı ilçesindeki Mehmet Soykan Ortaokulundaki 6-8. sınıf öğrencileri katılmıştır. Öğrencilerin özetleme becerilerini belirlemek için, araştırmacılar tarafından kolay, orta ve zor düzeyde birer öyküleyici ve bilgilendirici metin kullanılmıştır. Öğrencilerin farklı ders saatlerinde okuyup özetledikleri metinler, "Özet Metinleri Değerlendirme Ölçeği" kullanılarak puanlanmıştır. Özet metinlerin puanlanmasından elde edilen veriler, metin türü, metin güçlük düzeyi, akademik başarı, okuma alışkanlığı, sınıf düzeyi ve cinsiyet gibi değişkenler açısından incelenmiştir. Yapılan değerlendirmeler sonucunda, 6-8. sınıf ortaokul öğrencilerinin bilgilendirici ve öyküleyici metinleri özetleme becerilerinin zayıf düzeyde olduğu belirlenmiştir. Bununla birlikte ortaokul öğrencilerinin akademik başarı durumları, sınıf düzeyi ile özetleme becerileri arasında anlamlı bir ilişkinin olduğu; fakat metin güçlük düzeyi, kitap okuma

In this chapter, the authors present the results of the development the text-mining methodology for increasing the reliability of the functioning of the Integrated safety management system in Air Traffic Services as a Socio-Technical System (STS). Taking into account revealed strengths and weaknesses of Discriminant and Probabilistic approaches of Latent Semantic Relations analysis in of the abstracting and summarization projection, the Methodology of Two-level Single Document Summarization was developed. The Methodology assumes the following elements of novelty: based on obtaining a multi-level topical framework of the document (abstracting); uses the synergy effect of consistent usage the combination of two approaches for identification of conceptually significant elements of the text (summarization). Such approaches should help human to increase the quality of supporting the decision-making processes of STS in real time

This paper describes an efficient algorithm for language independent generic extractive summarization for single document. The algorithm is based on structural and statistical (rather than semantic) factors. Through evaluations performed on a single-document summarization for English, Hindi, Gujarati and Urdu documents, we show that the method performs equally well regardless of the language. The algorithm has been applied on DUC data for English documents and various newspaper articles for other languages with corresponding stop words list and modified stemmer. The results of summarization have been compared with DUC 2002 data using degree of representativeness. For other languages, the degree of representativeness we get is highly encouraging.

Summarized text is a simplified and condensed version of the original text containing highlighted information to help the audience get the gist in a short period of time. Typically, text summarization produces abstract or a paragraph-like outputs by omitting details and irrelevant information. However, the text summary can also be produced in a visualized form, such as a chart, graph or table representing a collection of similar cases. The visualized version generates a statistical-like presentation, which often involves numerical and ordinal observation of the gathered knowledge from the text. This requires lexical syntactic understanding of the text. Essential to achieve this goal is topic identification, message analysis/interpretation and knowledge summarization generation. The objective of this study is to model knowledge summarization problem using the evolving fuzzy grammar technique and we focus on metadata generation for producing visualized knowledge summarization. The process comprises of: (i) identifying the underlying structure of the texts for knowledge summarization, (ii) represent the identified knowledge for summarization manipulation and (iii) presentation of the summarized knowledge. A prototype called FTCat© is developed as a proof of concept and we demonstrate its practicality in summarizing news reports.

Text summarization is the core aspects of Natural Language processing. Summarized text should consist of unique sentences. It is used in many situations in today's Information technological word, one of the best examples is in understanding customer feedbacks in companies. This job can be done by humans, but if the text or data that has to be summarized then it will consume lot of time and work force. This situation lead to birth of different approaches in summarization. This paper addresses and concentrates on various methods and approaches and their results in abstractive text summarization. This survey gives an insight about different types of text summarization and various methods used in abstractive text summarization in recent developments.

The article exemplifies and presents the characteristics of linguistic imperialism, linguistic capital accumulation following the same pattern as capitalist economic dominance. The text summarizes the way English was established in the colonial period. Many of the mechanisms of linguistic hierarchy have been maintained and intensified since then, as African and Indian scholarship demonstrates. Language plays a key role in education, the World Bank taking over where colonial regimes left off. Anglo-American efforts to maintain global English dominance have intensified since 1945 and are central to the present-day world 'order', as the postcolonial is subsumed under global empire, assisted by English linguistic neoimperialism. Some scholars who deny the existence of linguistic imperialism are reported on, and the complexity of language policy in European integration is demonstrated. The article concludes by setting out how the deceptive term 'lingua franca' needs to be challenged, and lists ways of exploring English as project, process, and product, setting out key research questions. The constraints of a short article only permit glimpses of a rapidly evolving scene, the visible top of the English iceberg.

Due to substantial increase in the amount of information on the Internet, it has become extremely difficult to search for relevant documents needed by the users. To solve this problem, Text summarization is used which produces the summary of documents such that the summary contains important content of the document. This paper proposes a better approach for text summarization using lexical chaining and correlation of sentences. Lexical chains are created using Wordnet . The score of each Lexical chain is calculated based on keyword strength, Tf-idf & other features. The concept of using lexical chains helps to analyze the document semantically and the concept of correlation of sentences helps to consider the relation of sentence with preceding or succeeding sentence. This improves the quality of summary generated.

Focused Multi-Document Summarization (MDS) is concerned with summarizing documents in a collection with a concentration toward a particular external request (ie query, question, topic, etc.), or focus. Although the current state-of-the-art provides somewhat ...

Summarizing is restating the most important ideas from an original text briefly. Students often need summary writing skill along the education life since it provides understanding and remembering the reading material. This study aims to apply book summary writing strategy which is based on in-class implementations, and to develop the students book summary writing skill with education. With this aim, to determine students' book summary writing skill and analyze the development of their book summary writing skill, researchers have developed a book summary writing strategy and also a rubric to evaluate the written summaries. While developing the book summary writing strategy, researchers have conducted the study with 44 university students studying at Turkish language teaching department in the third grade. The study lasted for 11 weeks, and the education period is implemented as one week education and one week summary writing implementation. The strategy and rubric have been updated with the students' views, feedbacks and researchers' notes during the education process. In the study, of the qualitative research methods, grounded theory was used. At the end of the study, it is stated that students have been successful in writing a book summary, tagging and taking notes, isolating from trivial details and also, they could write the summaries in a shorter time. The study findings revealed the usable book summary writing strategy and the rubric for book summary evaluation.

A sentence extract summary of a document is a subset of the document's sentences that contains the main ideas in the document. We present two approaches to generating such summaries. The rst uses a pivoted QR decomposition of the term-sentence matrix in order to identify sentences that have ideas that are distinct from those in other sentences. The second is based on a hidden Markov model that judges the likelihood that each sentence should be contained in the summary. We compare the results of these methods with summaries generated by humans, showing that we obtain higher agreement than do earlier methods. pervasive use of information retrieval systems in the last 6 years this area has been given wider attention HM00]. For example, Microsoft Word has a built-in tool to summarize documents created by it. Such a summary is an example of a generic summary, i.e., one that attempts to capture the essential points of a document. In addition, summarization methods are regularly used by web search engines to give a brief synopsis of the documents retrieved by a user query. Such query-based summaries can be more focused, since the user's query terms are known to the retrieval system and can be used to target the summaries to the query.

The availability of online information shows a need of efficient text summarization system. The text summarization system follows extractive and abstractive methods. In extractive summarization, the important sentences are selected from the original text on the basis of sentence ranking methods. The Abstractive summarization system understands the main concept of texts and predicts the overall idea about the topic. This paper mainly concentrated the survey of existing extractive text summarization models. Numerous algorithms are studied and their evaluations are explained. The main purpose is to observe the peculiarities of existing extractive summarization models and to find a good approach that helps to build a new text summarization system.

The availability of online information shows a need of efficient text summarization system. The text summarization system follows extractive and abstractive methods. In extractive summarization, the important sentences are selected from the original text on the basis of sentence ranking methods. The Abstractive summarization system understands the main concept of texts and predicts the overall idea about the topic. This paper mainly concentrated the survey of existing extractive text summarization models. Numerous algorithms are studied and their evaluations are explained. The main purpose is to observe the peculiarities of existing extractive summarization models and to find a good approach that helps to build a new text summarization system.

It is now almost 15 years since the publication of the first paper on text mining in the genomics domain, and decades since the first paper on text mining in the medical domain. Enormous progress has been made in the areas of information retrieval, evaluation methodologies and resource construction. Some problems, such as abbreviationhandling, can essentially be considered solved problems, and others, such as identification of gene mentions in text, seem likely to be solved soon. However, a number of problems at the frontiers of biomedical text mining continue to present interesting challenges and opportunities for great improvements and interesting research. In this article we review the current state of the art in biomedical text mining or 'BioNLP' in general, focusing primarily on papers published within the past year.

Summarization of software artifacts is an ongoing field of research among the software engineering community due to the benefits that summarization provides like saving of time and efforts in various
software engineering tasks like code search, duplicate bug reports detection, traceability link recovery, etc.Summarization is to produce short and concise summaries. The paper presents the review of the state of the art of summarization techniques in software engineering context.

In many modern information retrieval applications, a common problem which arises is the existence of multiple documents covering similar information, as in the case of multiple news stories about an event or a sequence of events. A particular challenge for text summarization is to be able to summarize the similarities and differences in information content among these documents. The approach described here exploits the results of recent progress in information extraction to represent salient units of text and their relationships. By exploiting meaningful relations between units based on an analysis of text cohesion and the context in which the comparison is desired, the summarizer can pinpoint similarities and differences, and align text segments. In evaluation experiments, these techniques for exploiting cohesion relations result in summaries which (i) help users more quickly complete a retrieval task (ii) result in improved alignment accuracy over baselines, and (iii) improve identification of topic-relevant similarities and differences.

Text Summarization has always been an area of active interest in the academia. In recent times, even though several technique s have being developed for automatic text summarization, efficiency is still a concern. Given the increase in size and number of documents available online, an efficient automatic news summarizer is the need of the hour. In this paper, we propose a techn ique of text summarization which focuses on the problem of identifying the most important portions of the text and producing coherent summaries. People tend to read multiple news articles on a topic since a single article may not contain all important informa tion. A summary of all the articles related to topic will save the time and energy. In this research, an extractive based approach is used to generate a two-level summary from online news articles. News topics covered include politics, sports health, science and movie reviews from, etc. The first-level summary generates the summary of each article and second level summary combines the first level summaries and generates the final summary. To understand the variation of these news articles, Sentiment Analysis is a pplied.

Contextual advertising systems suggest suitable advertisings to users while surfing the Web. Focusing on text summarization, we propose novel techniques for contextual advertising. Comparative experiments between these techniques and existing ones have been performed.

During maintenance developers cannot read the entire code of large systems. They need a way to get a quick understanding of source code entities (such as, classes, methods, packages, etc.), so they can efficiently identify and then focus on the ones related to their task at hand. Sometimes reading just a method header or a class name does not tell enough about its purpose and meaning, while reading the entire implementation takes too long. We study a solution which mitigates the two approaches, i.e., short and accurate textual descriptions that illustrate the software entities without having to read the details of the implementation. We create such descriptions using techniques from automatic text summarization. The paper presents a study that investigates the suitability of various such techniques for generating source code summaries. The results indicate that a combination of text summarization techniques is most appropriate for source code summarization and that developers generally agree with the summaries produced.

Öz Özetleme, edinilen bilgilerin sınıflandırılmasını sağma işlemi ve mümkün olduğunca az kelimeyle metnin ana ifadesinin ortaya konulma sürecidir. Özetleme çalışmalarıyla beyin; sınıflandırma, analiz, açıklama, değerlendirme ve sonuç gibi bir dizi bilişsel işlem gerçekleştirmektedir. Özetlemede metnin eksiksiz olarak anlaşılması çok önemlidir. Metnin tam olarak anlaşılmasında ise metin dil bilim çalışmaları önemli bir yere sahiptir. Bu çalışmada Türk dili ve edebiyatı öğretmen adaylarının özetleme stratejilerini kullanım tercihleri incelenmiştir. Araştırma tarama deseninde modellenmiştir. Çalışmadaki veriler Deneme (2009) tarafından geliştirilen 14 maddelik 'Özetleme Stratejileri Ölçeği' kullanılarak elde edilmiş ve ölçeğin Crohach-alfa değeri 0.67 olarak tespit edilmiştir. Araştırma, 2011-2012 eğitim öğretim yılı güz döneminde Gazi Üniversitesi Türk dili ve edebiyatı öğretmenliği bölümünde öğrenim görmekte olan 63'ü kız (%66,3), 32'si (%33,7) erkek olmak üzere toplam 95 öğrenciden alınan verilerden yararlanılarak oluşturulmuştur. Anket aracılığıyla toplanan veriler istatistikî olarak, bağımsız örneklem t testi ve tek faktörlü varyans analizi (Anova) ile anlamlandırılmış ve sonuçlar tablolaştırılmıştır. Sonuç olarak öğretmen adaylarının özellikle kaynak metinde yer alan imge ve düşüncelerin özet metinde yer bulmasını sağlayacak bağlantı ve atıf stratejileri ile eş zamanlı özetleme gibi stratejileri yeterli düzeyde kullanmadığı tespit edilmiştir. Bu sonuçlar doğrultusunda edebiyat öğretmeni adaylarına özetleme eğitimi verilmesi ve bu eğitimin metin dil bilim verileri doğrultusunda gerçekleştirilmesi önerilmektedir. Anahtar Sözcükler: Özetleme, özetleme stratejileri, metin dil bilim, edebiyat öğretimi Abstract Summation is a process of both enabling the classification of the knowledge obtained and laying the main statement of a text barely by using a few words as soon as possible. By dint of summation works, brain carries out a series of cognitive transactions such as classification, analysis, explanation, assessment and conclusion. Understanding a text precisely has a very important place in summation. However, text linguistics studies have also great importance while understanding a text completely. In this study, summation strategies use preferences of Turkish Language and Literature teacher candidates are examined. The study is modeled in scanning pattern. The data in the study has been obtained by using 'Summation Strategies Scale' consisting of 14 articles, developed by Deneme (2009) and Crohach-alfa value of this scale has been determined as ,67. The study has been composed by benefiting from the data obtained from a total of 95 students 63 (%66,3) of which was female and 32 (%33,7) of which was male who had been studying in Gazi University Turkish Language and Literature Department during fall term of 2011-2012 academic year. The data collected by dint of a survey has gained meaning statistically by independent sample t test and single factoral variance analyzes (Anova) and the results have been tabulated. As a conclusion, it has been determined that teacher candidates didn't use connection and citation strategies enabling the images and ideas in source text to be present at summary text and the strategies

A novel technique is proposed for summarizing text using a combination of Genetic Algorithms (GA) and Genetic Programming (GP) to optimize rule sets and membership functions of fuzzy systems. The novelty of the proposed algorithm is that fuzzy system is optimized for extractive based text summarizing. In this method GP is used for structural part and GA for the string part (Membership functions). The goal is to develop an optimal intelligent system to extract important sentences in the texts by reducing the redundancy of data. The method is applied in 3 test documents and compared with the standard fuzzy systems as well as two other commercial summarizers: Microsoft word and Copernic Summarizer. Simulations demonstrate several significant improvements with the proposed approach.

News content is one of the most important factors that have influence on various sections. With the increase in the number of news it has got difficult for users to access news of their interest which makes it a necessity to categories news so that it could be easily accessed. By using data mining techniques, the news articles are categorized for easier navigation among articles. This will help users to access the news of their interest in real-time without wasting any time. Text Summarization reduces the effort and time consumption of the user instead of reading whole news article.

The article exemplifies and presents the characteristics of linguistic imperialism, linguistic capital accumulation following the same pattern as capitalist economic dominance. The text summarizes the way English was established in the colonial period. Many of the mechanisms of linguistic hierarchy have been maintained and intensified since then, as African and Indian scholarship demonstrates. Language plays a key role in education, the World Bank taking over where colonial regimes left off. Anglo-American efforts to maintain global English dominance have intensified since 1945 and are central to the present-day world 'order', as the postcolonial is subsumed under global empire, assisted by English linguistic neoimperialism. Some scholars who deny the existence of linguistic imperialism are reported on, and the complexity of language policy in European integration is demonstrated. The article concludes by setting out how the deceptive term 'lingua franca' needs to be challenged, and lists ways of exploring English as project, process, and product, setting out key research questions. The constraints of a short article only permit glimpses of a rapidly evolving scene, the visible top of the English iceberg.

In many modern information retrieval applications, a common problem which arises is the existence of multiple documents covering similar information, as in the case of multiple news stories about an event or a sequence of events. A particular challenge for text summarization is to be able to summarize the similarities and differences in information content among these documents. The approach described here exploits the results of recent progress in information extraction to represent salient units of text and their relationships. By exploiting meaningful relations between units based on an analysis of text cohesion and the context in which the comparison is desired, the summarizer can pinpoint similarities and differences, and align text segments. In evaluation experiments, these techniques for exploiting cohesion relations result in summaries which (i) help users more quickly complete a retrieval task (ii) result in improved alignment accuracy over baselines, and (iii) improve identification of topic-relevant similarities and differences.

One of the main challenges faced by today's developers is keeping up with the staggering amount of source code that needs to be read and understood. In order to help developers with this problem and reduce the costs associated with it, one solution is to use simple textual descriptions of source code entities that developers can grasp easily, while capturing the code semantics precisely. We propose an approach to automatically determine such descriptions, based on automated text summarization technology.

Automatic text summarization helps the user to quickly understand large volumes of information. We present a language-and domain-independent statistical-based method for single-document extractive summarization, i.e., to produce a text summary by extracting some sentences from the given text. We show experimentally that words that are parts of bigrams that repeat more than once in the text are good terms to describe the text's contents, and so are also so-called maximal frequent sentences. We also show that the frequency of the term as term weight gives good results (while we only count the occurrences of a term in repeating bigrams).

The main problem for generating an extractive automatic text summary is to detect the most relevant information in the source document. Although, some approaches claim being domain and language independent, they use high dependence knowledge like key-phrases or golden samples for machine-learning approaches. In this work, we propose a language-and domain-independent automatic text summarization approach by sentence extraction using an unsupervised learning algorithm. Our hypothesis is that an unsupervised algorithm can help for clustering similar ideas (sentences). Then, for composing the summary, the most representative sentence is selected from each cluster. Several experiments in the standard DUC-2002 collection show that the proposed method obtains more favorable results than other approaches.

In this study, problems faced by pre-service Turkish language teachers during summarizing the texts listened were studied. The study was performed with 202 pre-service teachers studying at the fourth grade of Turkish Language Education department at Gazi University and Mustafa Kemal University in 2013-2014 academic year. In the study, informative, narrative and argumentative text summarizations were evaluated in view of summarizing strategies as writing title, using perspective in a correct way, using mode of expression properly, deciding on important information, erasing unimportant information, not including a non-textual information, coherent writing and abridgment. In the result of evaluation, the problems experienced in summarizing were determined. With this goal, criterion summary was created for each of the informative, narrative and argumentative texts, and analysis were carried out via “Inventory of Summarizing Problem” developed by the researcher.  The uses matching up with the criterion summary were admitted successful and the different uses were seen as a problem. In the study the problems confronted by students about summarization were determined like these: Not writing a title, using a title different from the original, writing the summary from several perspectives, summarizing through the first-person singular perspective, using more than one mode of expression, writing with a completely wrong mode of expression, summarizing with very little important information, summarizing with a lot of unimportant information, included several non-textual information, including conflicting information, not doing sentence and paragraph transitions, not maintaining textual integrity, writing too long or too short.

Keywords: Listening Education, Summarizing Skills for the Texts Listened, Summarization Strategies.

Özet
Bu çalışmada, Türkçe öğretmeni adaylarının dinlediğini özetlemede karşılaştıkları sorunlar ele alınmıştır. Çalışma, 2013-2014 öğretim yılında Gazi ve Mustafa Kemal Üniversitesi Türkçe Eğitimi Bölümü’nde okuyan dördüncü sınıf 202 öğretmen adayı ile gerçekleştirilmiştir. Çalışmada bilgilendirici, öyküleyici ve tartışmacı metin özetleri; başlık yazma, bakış açısını doğru kullanma, anlatım kipini doğru kullanma, önemli bilgiyi seçme, önemsiz bilgiyi silme, metin dışı bilgiye yer vermeme, tutarlı yazma ve kısaltma şeklinde belirlenen özetleme stratejileri açısından değerlendirilmiş, değerlendirme sonucunda özetleme konusunda yaşanan sorunlar tespit edilmiştir. Bu amaç doğrultusunda bilgilendirici, öyküleyici ve tartışmacı metinlerin her biri için ölçüt özet oluşturulmuş, analizler, araştırmacı tarafından geliştirilen “Özetleme Sorun Envanteri” kullanılarak gerçekleştirilmiştir. Ölçüt özete uyan kullanımlar başarılı olarak kabul edilmiş, uymayan kullanımlar, birer sorun olarak görülmüştür. Çalışmada, öğrencilerin özetleme konusunda yaşadıkları sorunlar şu şekilde tespit edilmiştir: Başlık yazmama, orijinalinden farklı başlık kullanma, özeti birden çok bakış açısıyla yazma, birinci tekil şahıs bakış açısı ile özetleme, birden çok anlatım kipi kullanma, tamamen yanlış anlatım kipi ile yazma, az sayıda önemli bilgi ile özetleme, çok sayıda önemsiz bilgi ile özetleme, birtakım metin dışı bilgilere yer verme, birbiriyle çelişen bilgilere yer verme, cümle ve paragraf geçişlerini yapmama, konu bütünlüğünü sağlayamama, çok uzun veya çok kısa yazma.

Anahtar Kelimeler: Dinleme Eğitimi, Dinlediğini Özetleme Becerisi, Özetleme Stratejileri

An experiment was designed to test the hypothesis that second language (L2) students' approach to text reflects a top-down processing strategy in contrast to first language (Ll) students' approach which is more text-driven. Forty students in two Advanced Level English as a Foreign Language classes were asked to read authentic academic texts either in L2 (between 3345-4305 words) or translated into their L1, and to write short (150-200 words) summaries of the texts in L1. To identify the reading process involved, the activities of underlining, marking, and note-taking were analysed. The summaries were analysed according to eight categories of information grouped into four classes of operations: Selection, Abstraction, Cohesion, and Addition.

A multiple-perspective co-citation analysis method is introduced for characterizing and interpreting the structure and dynamics of co-citation clusters. The method facilitates analytic and sense making tasks by integrating network visualization, spectral clustering, automatic cluster labeling, and text summarization. Co-citation networks are decomposed into co-citation clusters. The interpretation of these clusters is augmented by automatic cluster labeling and summarization. The method focuses on the interrelations between a co-citation cluster's members and their citers. The generic method is applied to a three-part analysis of the field of Information Science as defined by 12 journals published between 1996 and 2008: 1) a comparative author co-citation analysis (ACA), 2) a progressive ACA of a time series of co-citation networks, and 3) a progressive document co-citation analysis (DCA). Results show that the multipleperspective method increases the interpretability and accountability of both ACA and DCA networks.

The task of automatic text summarization consists of generating a summary of the original text that allows the user to obtain the main pieces of information available in that text, but with a much shorter reading time. This is an increasingly important task in the current era of information overload, given the huge amount of text available in documents. In this paper the automatic text summarization is cast as a classification (supervised learning) problem, so that machine learning-oriented classification methods are used to produce summaries for documents based on a set of attributes describing those documents. The goal of the paper is to investigate the effectiveness of Genetic Algorithm (GA)-based attribute selection in improving the performance of classification algorithms solving the automatic text summarization task. Computational results are reported for experiments with a document base formed by news extracted from The Wall Street Journal of the TIPSTER collection–a collection that is often used as a benchmark in the text summarization literature.

Web advertising, one of the major sources of income for a large number of Web sites, is aimed at suggesting products and services to the ever growing population of Internet users. A significant part of Web advertising consists of textual ads, the ubiquitous short text messages usually marked as sponsored links. There are two primary channels for distributing ads: Sponsored Search (or Paid Search Advertising) and Content Match (or Contextual Advertising). In this paper, we concentrate on the latter, which is devoted to display commercial ads within the content of third-party Web pages. In the literature, several approaches estimated the ad relevance based on co-occurrence of the same words or phrases within the ad and within the page. However, targeting mechanisms based solely on phrases found within the text of the page can lead to problems. In order to solve these problems, matching mechanisms that combine a semantic phase with the traditional syntactic phase have been proposed. We are mainly interested in studying the impact of the syntactic phase on contextual advertising. In particular, we perform a comparative study on text summarization in contextual advertising. Results show that implementing effective text summarization techniques may help to improve the corresponding contextual advertising system.

Scientific literature records the research process with a standardized structure and provides the clues to track the progress in a scientific field. Understanding its internal structure and content is of paramount importance for natural language processing (NLP) technologies. To meet this requirement, we have developed a multi-layered annotated corpus of scientific papers in the domain of Computer Graphics. Sentences are annotated with respect to their role in the argumentative structure of the discourse. The purpose of each citation is specified. Special features of the scientific discourse such as advantages and disadvantages are identified. In addition, a grade is allocated to each sentence according to its relevance for being included in a summary.To the best of our knowledge, this complex, multi-layered collection of annotations and metadata characterizing a set of research papers had never been grouped together before in one corpus and therefore constitutes a newer, richer resource with respect to those currently available in the field.

There are sixteen known methods for automatic text summarization. In our study we will use Natural language processing NLP within hybrid approach that will improve the quality of important sentences selection by thickening sentence score along with reducing the number of long sentences that would be included in the final summarization. The based approach which is used in the algorithm is Term Occurrences.

Text summarization is the process of automatically creating a compressed version of a given document preserving its information content. There are two types of summarization: extractive and abstractive. Extractive summarization methods simplify the problem of summarization into the problem of selecting a representative subset of the sentences in the original documents. Abstractive summarization may compose novel sentences, unseen in the original sources. In our study we focus on sentence based extractive document summarization. The extractive summarization systems are typically based on techniques for sentence extraction and aim to cover the set of sentences that are most important for the overall understanding of a given document. In this paper, we propose unsupervised document summarization method that creates the summary by clustering and extracting sentences from the original document. For this purpose new criterion functions for sentence clustering have been proposed. Similarity measures play an increasingly important role in document clustering. Here we've also developed a discrete differential evolution algorithm to optimize the criterion functions. The experimental results show that our suggested approach can improve the performance compared to sate-of-the-art summarization approaches.

Text segmentation is a fundamental problem in natural language processing, which has application in information retrieval, question answering, and text summarization. Almost previous works on unsupervised text segmentation are based on the assumption of lexical cohesion, which is indicated by relations between words in the two units of text. However, they only take into account the reiteration, which is a category of lexical cohesion, such as word repetition, synonym or superordinate. In this research, we investigate the non-systematic semantic relation, which is classified as collocation in lexical cohesion. This relation holds between two words or phrases in a discourse when they pertain to a particular theme or topic. This relation has been recognized via a topic model, which is, in turn, acquired from a large collection of texts. The experimental results on the public dataset show the advantages of our approach in comparison to the available unsupervised approaches.