Summarization Of News Articles Research Articles

A Comparative Study of Transformer-based Models for Text Summarization of News Articles

Transformer-based models such as GPT, T5, BART, and PEGASUS have made substantial progress in text summarization, a sub-domain of natural language processing that entails extracting important information from lengthy texts. The main objective of this research was to conduct a comparative analysis of these four transformer-based models based on their performance in text summarization of news articles. In achieving this objective, the transformer models pre-trained on extensive datasets were fine-tuned on the CNN/DailyMail dataset using a low learning rate to preserve the learned representations. The T5 transformer records the highest scores of 35.12, 22.75, 32.82, and 28.59 in ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-Lsum respectively, surpassing GPT, BART, and PEGASUS across all ROUGE metrics. The findings deduced from this study establish the proficiency of encoder-decoder models such as T5 in summary generation. Furthermore, the findings also demonstrated that the fine-tuning process's effectiveness in pre-trained models is improved when the pre-training objective closely aligns with the downstream task.

The Method of Automatic Construction of Training Collections for the Task of Abstractive Summarization of News Articles

The Method of Automatic Construction of Training Collections for the Task of Abstractive Summarization of News Articles

Comparative Analysis of Text Mining Techniques for News Article Summarization

Comparative Analysis of Text Mining Techniques for News Article Summarization

NewsIN: A News Summarizer and Analyzer

Abstract: A summary condenses a lengthy document by highlighting salient features. It helps the reader to understand completely just by reading a summary so that the reader can save time and also can decide whether to go through the entire document. Summaries should be shorter than the original article so make sure to select only pertinent information to include the article. The main goal of a newspaper article summary is, the readers to walk away with knowledge on what the newspaper article is all about without the need to read the entire article. This work proposes a news article summarization system which access information from various local online newspapers automatically and summarizes information using heterogeneous articles. To make ad-hoc keyword-based extraction of news articles, the system uses a tailor-made web crawler which crawls the websites for searching relevant articles. Computational Linguistic techniques mainly Triplet Extraction, Semantic Similarity calculation and OPTICS clustering with DBSCAN is used alongside a sentence selection heuristic to generate coherent and cogent summaries irrespective of the number of articles supplied to the engine. The performance evaluation is one using the ROUGE metric. The rapid progresses in digital data acquisition techniques have led to a huge volume of news data available in the news websites. Most of such digital news collections lack summaries. Due to that, online newspaper readers are overloaded with lengthy text documents. Also, it is a tedious task for human beings to generate an abstract for a news event manually since it requires a rigorous analysis of the news documents. An achievable solution tothis problem is condensing the digital news collections and taking out only the essence in the form of an automatically generated summary which allows readers to make effective decisions in less time. The graph based algorithms for text summarization have been proven to be very successful over other methods for producing multi document summaries. The summary generated fromknowledge graphs is more in line with human reading habits and possesses the logic of human reasoning. Due to the fast-growing need of retrieving information in abstract form, we are proposing a novel approach for abstractive news summarization using the knowledge graphs to fulfill the need of having more accurate automatic abstractive news summarization and analyzer

Improved Text Summarization of News Articles Using GA-HC and PSO-HC

Automatic Text Summarization (ATS) is gaining attention because a large volume of data is being generated at an exponential rate. Due to easy internet availability globally, a large amount of data is being generated from social networking websites, news websites and blog websites. Manual summarization is time consuming, and it is difficult to read and summarize a large amount of content. Automatic text summarization is the solution to deal with this problem. This study proposed two automatic text summarization models which are Genetic Algorithm with Hierarchical Clustering (GA-HC) and Particle Swarm Optimization with Hierarchical Clustering (PSO-HC). The proposed models use a word embedding model with Hierarchal Clustering Algorithm to group sentences conveying almost same meaning. Modified GA and adaptive PSO based sentence ranking models are proposed for text summary in news text documents. Simulations are conducted and compared with other understudied algorithms to evaluate the performance of proposed methodology. Simulations results validate the superior performance of the proposed methodology.

Event-based summarization of news articles

In recent years, with the increase of available digital information on the Web, the time needed to find relevant information is also increased. Therefore, to reduce the time spent on searching, research on automatic text summarization has gained importance. The proposed summarization process is based on event extraction methods and is called an event-based extractive single-document summarization. In this method, the important features of event extraction and summarization methods are analyzed and combined together to extract the summaries from single-source news documents. Among the tested features, six features are found to be the most effective in constructing good summaries. The constructed summaries are tested on benchmark Document Understanding Conferences 2001 and 2002 datasets, and the results outperformed most of the other well-known summarization methods.

Does Summarization Help Stock Prediction? A News Impact Analysis

The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.

Proactive News Article Summarization Service Using Personal Intention Models

Nowadays, we live with a huge amount of data. By IDC report, the amount of data generated in 2011 is about 1.8 ZB (trillion GB). Ironically, there are small amount of useful information when you are looking at a number of papers, internet articles, movies, pictures, and social network posts. As a result, it is required that users extract useful information manually. However, this is tedious and hard task. To solve this problem, a lot of sophisticated techniques have been proposed to provide summarization service. Although each user has different desire on the summarization, the service uses much computational resource to produce standard summarization for all users. In this study, we propose to use machine learning to predict the intention of users on the summarization. It can reduce the computational cost to summarize all the documents and make available proactive summarization service. To validate our proposal, we run experiments with eight participants for two news portals on five topic areas.

Topic aspect-oriented summarization via group selection

The summarization is desirable to efficiently apprehend the gist of the huge amount of data and becomes a significant challenge in many applications such as news article summarization and social media mining. Considering the summaries from multi-documents of one topic can describe various aspects of one given topic, this paper attempts to exploit appropriate priors to generate topic aspect-oriented summarization (abbreviated as TAOS). The underlying intuition of the proposed TAOS is that different topics can prefer different aspects and the different aspects can be represented by different preference of features(e.g., technical topic may prefer proper noun than sports topic). In order to materialize the intuition of TAOS, we first extract several groups of features according to topic factors, and then a group norm penalty (i.e., ℓ1/ℓ2 norm) and latent variables are utilized to select overlapping groups of features. We compare our proposed approach with some state-of-the-art methods on DUC2003, DUC2004 datasets for text summarization and NUS-Wide dataset for image summarization. The results show our method can generate meaningful summarization in terms of ROUGE and Jensen–Shannon Divergence metrics.

An Effective Approach for News Article Summarization

Information on the World Wide Web and in other electronic form is increasing tremendously. Therefore there is a need for some form of information compression which can be achieved by various mining tasks like classification, clustering and summarization that help in understanding the information. Large amount of web content is news. News websites are daily overwhelmed with plenty of news articles. This paper presents an effective approach for single document news article summarization to help people obtain the most important information in the shortest time. The proposed approach is query based news article summarization. The results from web based on user query are filtered and refined and then result is directed to user. The technique used for summarization is keyword based extractive summarization.

Multi‐document summarization of news articles using an event‐based framework

PurposeThe purpose of this research is to develop a method for automatic construction of multi‐document summaries of sets of news articles that might be retrieved by a web search engine in response to a user query.Design/methodology/approachBased on the cross‐document discourse analysis, an event‐based framework is proposed for integrating and organizing information extracted from different news articles. It has a hierarchical structure in which the summarized information is presented at the top level and more detailed information given at the lower levels. A tree‐view interface was implemented for displaying a multi‐document summary based on the framework. A preliminary user evaluation was performed by comparing the framework‐based summaries against the sentence‐based summaries.FindingsIn a small evaluation, all the human subjects preferred the framework‐based summaries to the sentence‐based summaries. It indicates that the event‐based framework is an effective way to summarize a set of news articles reporting an event or a series of relevant events.Research limitations/implicationsLimited to event‐based news articles only, not applicable to news critiques and other kinds of news articles. A summarization system based on the event‐based framework is being implemented.Practical implicationsMulti‐document summarization of news articles can adopt the proposed event‐based framework.Originality/valueAn event‐based framework for summarizing sets of news articles was developed and evaluated using a tree‐view interface for displaying such summaries.