A Study on Abstractive Summarization Techniques in Indian Languages

The amount of data available in the internet is increasing at a very high speed. Text summarization has helped in making a better use of the information available online. Various methods were adopted to automate text summarization. However there is no existing system for summarizing Malayalam documents. In this paper we have investigated on developing efficient and effective methods to summarize Malayalam documents. This paper explains a statistical sentence scoring technique and a semantic graph based technique for text summarization.

Text summarization for Malayalam documents — An experience

Today in the era of Big Data, textual data is rapidly growing and is available in many different languages. In the fast-moving world, it's difficult to read all the text-content. Hence, the need for text summarization is being in the spotlight. Automatic text summarization is a technique which compresses large text to a shorter text which includes the important information. There are two types of summaries: Extractive summaries and Abstractive summaries. Extractive summaries are produced by extracting the whole sentences from the source text. Abstractive summaries are produced by reformulating sentences of the source text. Several text summarization techniques have been proposed in past years for English and various European languages but there are very few techniques that can be found for native languages of India. This paper presents a survey of text summarization techniques for various Indian and foreign languages like English, European, etc. Also, an approach for summarizing Hindi text using machine learning technique has been proposed. We have also described few challenges which are still under research.

A survey of automatic text summarization techniques for Indian and foreign languages

258 DOI: http://dx.doi.org/10.37398/JSR.2020.640149 Abstract: In the era of digital world, online information is growing exponentially. It leads to emergence of inconvenient searching of relevant information in relevant time. In this regard, automatic text summarizer proves to be a good tool. It helps in creating a brief and meaningful form of the given text using natural language tool kit so that users can access the information in quick manner. Today, a lot of summarization tools are available for rich resource languages such as English. But, it seems difficult to summarize the text for Indian languages (low resource languages) due to limited availability of NLP tools and techniques for Indian languages. In this paper, we present a survey on existing text summarization methods and NLP tools for Indian languages. We also discuss about the issues associated with the Indian languages that are the bottlenecks for summarizing Indian language text.

/pdf/accountability-of-nlp-tools-in-text-summarization-for-indian-1xc1qtbt40.pdf

Accountability of NLP Tools in Text Summarization for Indian Languages

Text summarization plays an important problem in natural language understanding and information retrieval. Automatic text summarization get much more attention by people presently because it is efficiently and effectively serve time in decision making process even for day to day life. Presently deep learning models get more attention than the traditional approaches. The primary objective of this research work is to propose a methodology to address the problem of summarization for Tamil sports news which can automatically create extractive summary for the news data with the use of Natural Language Processing (NLP) and a generic stochastic artificial neural network. Features such as sentence position, sentence position related to paragraph, number of named entities, term frequency and inverse document frequency and Number of numerals are employed to construct the feature matrix for each sentence and Restricted Boltzmann Machine is used to improve those features while enhancing the accuracy without loosing the main idea of the text. Experimentation is carried out using Online Tamil sports news and ROUGE tool kit is used to evaluate the recall, precision and F-measure for the summary generated by both the human experts and the system.

Text Summarization for Tamil Online Sports News Using NLP

Document summarization refers to the task of producing shorter version of the original document by selecting important sentences from the text. Tamil Document Summarization using sub graph presents a method for extracting sentences from an individual document to serve as a document summary or a pre-cursor to creating a generic document abstract. Language-Neutral Syntax (LNS), a system of representation for natural language sentences has been used for considering the semantics of the documents. Syntactic analysis of the text that produces a logical form analysis has been applied for each sentence. Subject-Object-Predicate (SOP) triples are extracted from individual sentences to create a semantic graph [2] of the original document and the corresponding human extracted summary. Semantic Normalization is applied to SOP triples to reduce the number of nodes in the semantic graph of the original document. Using the Support Vector Machine (SVM) learning algorithm, a classifier has been trained to identify SOP triples from the document semantic graph that belong to the summary. The classifier is then used for automatic extraction of summaries from the test documents.

M. Banu

Papers

Tamil Document Summarization Using Semantic Graph Method