Automatic Text Summaration of COVID-19 Scientific Research Topics Using Pre-trained Model from HuggingFace®

Word Clouds ◽

Readability Test ◽

By identifying and extracting relevant information from articles, automated text summarizing helps the scientific and medical sectors. Automatic text summarization is a way of compressing text documents so that users may find important information in the original text in less time. We will first review some new works in the field of summarizing that use deep learning approaches, and then we will explain the "COVID-19" summarization research papers. The ease with which a reader can grasp written text is referred to as the readability test. The substance of text determines its readability in natural language processing. We constructed word clouds using the abstract's most commonly used text. By looking at those three measurements, we can determine the mean of "ROUGE-1", "ROUGE-2", and "ROUGE-L". As a consequence, "Distilbart-mnli-12-6" and "GPT2-large" are outperform than other. <br>

Narzędzia do automatycznego streszczania tekstów w języku polskim. Stan badań naukowych i prac wdrożeniowych

e-mentor ◽

10.15219/em89.1513 ◽

2021 ◽

Vol 89 (2) ◽

pp. 67-77

Author(s):

Piotr Glenc ◽

Keyword(s):

Original Text ◽

Text Documents ◽

Computer Scientists ◽

Polish Language ◽

Subject Areas ◽

Automatic Abstracting ◽

State Of Research ◽

Automatic Text ◽

Language Text

The goal of the publication is to present the state of research and works carried out in Poland on the issue of automatic text summarization. The author describes principal theoretical and methodological issues related to automatic summary generation followed by the outline of the selected works on the automatic abstracting of Polish texts. The author also provides three examples of IT tools that generate summaries of texts in Polish (Summarize, Resoomer, and NICOLAS) and their characteristics derived from the conducted experiment, which included quality assessment of generated summaries using ROUGE-N metrics. The results of both actions showed a deficiency of tools allowing to automatically create summaries of Polish texts, especially in the abstractive approach. Most of the proposed solutions are based on the extractive method, which uses parts of the original text to create its abstract. There is also a shortage of tools generating one common summary of many text documents and specialized tools generating summaries of documents related to specific subject areas. Moreover, it is necessary to intensify works on creating the corpora of Polish-language text summaries, which the computer scientists could apply to evaluate their newly developed tools.

Developing a new approach to summarize Arabic text automatically using syntactic and semantic analysis

International Journal of Engineering & Technology ◽

10.14419/ijet.v9i2.30324 ◽

2020 ◽

Vol 9 (2) ◽

pp. 342

Author(s):

Amal Alkhudari

Keyword(s):

Language Processing ◽

Automatic System ◽

Semantic Analysis ◽

Text Summarization ◽

Original Text ◽

Arabic Text ◽

Wide Spread ◽

New Approach ◽

Due to the wide spread information and the diversity of its sources, there is a need to produce an accurate text summary with the least time and effort. This summary must preserve key information content and overall meaning of the original text. Text summarization is one of the most important applications of Natural Language Processing (NLP). The goal of automatic text summarization is to create summaries that are similar to human-created ones. However, in many cases, the readability of created summaries is not satisfactory, because the summaries do not consider the meaning of the words and do not cover all the semantically relevant aspects of data. In this paper we use syntactic and semantic analysis to propose an automatic system of Arabic texts summarization. This system is capable of understanding the meaning of information and retrieves only the relevant part. The effectiveness and evaluation of the proposed work are demonstrated under EASC corpus using Rouge measure. The generated summaries will be compared against those done by human and precedent researches.

Techniques and Issues in Text Mining

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9079 ◽

2020 ◽

Vol 17 (9) ◽

pp. 4368-4374

Author(s):

Perpetua F. Noronha ◽

Madhu Bhan

Keyword(s):

Language Processing ◽

Text Summarization ◽

Digital Data ◽

Text Documents ◽

Significant Information ◽

Digital Era ◽

Text Content ◽

Available Information ◽

Digital data in huge amount is being persistently generated at an unparalleled and exponential rate. In this digital era where internet stands the prime source for generating incredible information, it is vital to develop better means to mine the available information rapidly and most capably. Manual extraction of the salient information from the large input text documents is a time consuming and inefficient task. In this fast-moving world, it is difficult to read all the text-content and derive insights from it. Automatic methods are required. The task of probing for relevant documents from the large number of sources available, and consuming apt information from it is a challenging task and is need of the hour. Automatic text summarization technique can be used to generate relevant and quality information in less time. Text Summarization is used to condense the source text into a brief summary maintaining its salient information and readability. Generating summaries automatically is in great demand to attend to the growing and increasing amount of text data that is obtainable online in order to mark out the significant information and to consume it faster. Text summarization is becoming extremely popular with the advancement in Natural Language Processing (NLP) and deep learning methods. The most important gain of automatic text summarization is, it reduces the analysis time. In this paper we focus on key approaches to automatic text summarization and also about their efficiency and limitations.

Narzędzia do automatycznego streszczania tekstów w języku polskim. Stan badań naukowych i prac wdrożeniowych

e-mentor ◽

10.15219/em88.1513 ◽

2021 ◽

Vol 89 (2) ◽

pp. 67-77

Author(s):

Piotr Glenc ◽

Keyword(s):

Original Text ◽

Text Documents ◽

Computer Scientists ◽

Polish Language ◽

Subject Areas ◽

Automatic Abstracting ◽

State Of Research ◽

Automatic Text ◽

Language Text

The goal of the publication is to present the state of research and works carried out in Poland on the issue of automatic text summarization. The author describes principal theoretical and methodological issues related to automatic summary generation followed by the outline of the selected works on the automatic abstracting of Polish texts. The author also provides three examples of IT tools that generate summaries of texts in Polish (Summarize, Resoomer, and NICOLAS) and their characteristics derived from the conducted experiment, which included quality assessment of generated summaries using ROUGE-N metrics. The results of both actions showed a deficiency of tools allowing to automatically create summaries of Polish texts, especially in the abstractive approach. Most of the proposed solutions are based on the extractive method, which uses parts of the original text to create its abstract. There is also a shortage of tools generating one common summary of many text documents and specialized tools generating summaries of documents related to specific subject areas. Moreover, it is necessary to intensify works on creating the corpora of Polish-language text summaries, which the computer scientists could apply to evaluate their newly developed tools.

SGATS: Semantic Graph-based Automatic Text Summarization from Hindi Text Documents

ACM Transactions on Asian and Low-Resource Language Information Processing ◽

10.1145/3464381 ◽

2021 ◽

Vol 20 (6) ◽

pp. 1-32

Author(s):

Manju Lata Joshi ◽

Nisheeth Joshi ◽

Namita Mittal

Keyword(s):

Language Processing ◽

Semantic Analysis ◽

Text Summarization ◽

Original Text ◽

Theoretic Approach ◽

Extractive Summarization ◽

Semantic Graph ◽

Text Document ◽

Creating a coherent summary of the text is a challenging task in the field of Natural Language Processing (NLP). Various Automatic Text Summarization techniques have been developed for abstractive as well as extractive summarization. This study focuses on extractive summarization which is a process containing selected delineative paragraphs or sentences from the original text and combining these into smaller forms than the document(s) to generate a summary. The methods that have been used for extractive summarization are based on a graph-theoretic approach, machine learning, Latent Semantic Analysis (LSA), neural networks, cluster, and fuzzy logic. In this paper, a semantic graph-based approach SGATS (Semantic Graph-based approach for Automatic Text Summarization) is proposed to generate an extractive summary. The proposed approach constructs a semantic graph of the original Hindi text document by establishing a semantic relationship between sentences of the document using Hindi Wordnet ontology as a background knowledge source. Once the semantic graph is constructed, fourteen different graph theoretical measures are applied to rank the document sentences depending on their semantic scores. The proposed approach is applied to two data sets of different domains of Tourism and Health. The performance of the proposed approach is compared with the state-of-the-art TextRank algorithm and human-annotated summary. The performance of the proposed system is evaluated using widely accepted ROUGE measures. The outcomes exhibit that our proposed system produces better results than TextRank for health domain corpus and comparable results for tourism corpus. Further, correlation coefficient methods are applied to find a correlation between eight different graphical measures and it is observed that most of the graphical measures are highly correlated.

An Exhaustive Survey on Automatic Text Summarization Using Machine Learning Approches

Webology ◽

10.14704/web/v18si05/web18299 ◽

2021 ◽

Vol 18 (05) ◽

pp. 1184-1190

Author(s):

Abinaya N ◽

Anand R ◽

Arunkumar T ◽

Sameema Begam S

Keyword(s):

Machine Learning ◽

Natural Language Processing ◽

Language Processing ◽

Document Analysis ◽

Text Summarization ◽

Learning Approaches ◽

Grammatical Errors ◽

E Learning ◽

Automatic Text Summarization (ATS) is the key challenge in the area of Natural Language Processing (NLP). It deals with generalizing a summary from a given text without losing the vital information. This is a contemporary area because of exponential content growth in internet and applied in summarizing the content available in books, newsletters, internal document analysis, patent research, e-learning etc. Various machine learning approaches are used in order to achieve the performance of human-generated summaries. The system fails to perform at few areas like checking grammatical errors and paraphrasing the sentences after the summary creation. This work provides a brief view on methods and approaches used in ATS.

Statistical Features for Extractive Automatic Text Summarization

Natural Language Processing ◽

10.4018/978-1-7998-0951-7.ch030 ◽

2020 ◽

pp. 619-637

Author(s):

Yogesh Kumar Meena ◽

Dinesh Gopalani

Keyword(s):

Big Data ◽

Performance Measures ◽

Relevant Information ◽

Text Summarization ◽

Statistical Features ◽

Information Need ◽

Evaluation Measures ◽

Large Size ◽

Automatic Text Summarization (ATS) enables users to save their precious time to retrieve their relevant information need while searching voluminous big data. Text summaries are sensitive to scoring methods, as most of the methods requires to weight features for sentence scoring. In this chapter, various statistical features proposed by researchers for extractive automatic text summarization are explored. Features that perform well are termed as best features using ROUGE evaluation measures and used for creating feature combinations. After that, best performing feature combinations are identified. Performance evaluation of best performing feature combinations on short, medium and large size documents is also conducted using same ROUGE performance measures.

2020 International Conference on Electronics and Sustainable Communication Systems (ICESC) ◽

Automatic Text Summarization and Keyword Extraction using Natural Language Processing

10.1109/icesc48915.2020.9155852 ◽

2020 ◽

Author(s):

Avinash Payak ◽

Saurabh Rai ◽

Kanishka Shrivastava ◽

Reshma Gulwani

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Text Summarization ◽

Keyword Extraction ◽

Text Summarization

International Journal Of Engineering And Computer Science ◽

10.18535/ijecs/v9i2.4437 ◽

2020 ◽

Vol 9 (2) ◽

pp. 24940-24945

Author(s):

A. Vikas ◽

Pradyumna G.V.N ◽

Tahir Ahmed Shaik

Keyword(s):

Relevant Information ◽

Text Summarization ◽

The Internet ◽

Human Beings ◽

New Era ◽

Meaningful Information ◽

In this new era, where tremendous information is available on the internet, it is most important to provide the improved mechanism to extract the information quickly and most efficiently. It is very difficult for human beings to manually extract the summary of a large documents of text. There are plenty of text material available on the internet. So, there is a problem of searching for relevant documents from the number of documents available and absorbing relevant information from it. In order to solve the above two problems, the automatic text summarization is very much necessary. Text summarization is the process of identifying the most important meaningful information in a document or set of related documents and compressing them into a shorter version preserving its overall meanings.