Extractive Summarization Research Articles

Location-aware Extractive Text Summarization Using AI Techniques

Location-aware Extractive Text Summarization Using AI Techniques

Comparison of feature-based sentence ranking methods for extractive summarization of Turkish news texts

Comparison of feature-based sentence ranking methods for extractive summarization of Turkish news texts

An Efficient Summarisation and Search Tool for Research Articles

Building an efficient summarization and search tool for research articles is a complex task that involves interdisciplinary expertise in NLP, database management, web development, and user experience design. With the rapid growth of the scientific content, manually reading and selecting important content of research articles became challenging. Thus, there is a need for a summarization tool to help scholars reading their content fast along with a search tool that will find important contents and keep them in organized way. To summarize the contents of different articles a summarization tool is proposed in this work that generates extractive and abstractive summaries. Along with summarization a search engine also been proposed in this work that save the searched results in a comma-separated value (CSV) format including the search queries and meta information of articles such as keyword, title, author name, URL, year of publication, abstracts and summaries. These CSVs help users to get idea about article contents in offline mode without reading or searching the whole text. The efficiency of the summarizer tool is evaluated in terms of precision(pr), recall(re) and F-measure(F-m) of Rouge-1(R1), Rouge-2(R2), Rouge_sum(R_sum) and Bertscore(BS) measures for ten research articles. The average pr, re and F-m obtained from BS are 42%, 42% and 42% for extractive summarization and 41%, 41% and 41% for abstractive summarization. This tool will be helpful to research scholars in the collection of literature and the preparation of related work for their research.

A Probabilistic Approach for Extractive Summarization Based on Clustering Cum Graph Ranking Method

A Probabilistic Approach for Extractive Summarization Based on Clustering Cum Graph Ranking Method

DOMINER: Domain Feature Mining from Unstructured Data for Effective Text Summarization

In the current era of internet, a huge volume of opinionated sentiment reviews is generated on a daily basis. Normally, such reviews are enriched with deep sentiments and express the opinions on various features of a product or service under consideration. Identification of a set of important domain features opens an opportunity to build automatic product and service summarization system. It is observed that the common phenomena is to consider the frequently appearing words as the domainb features. However, not all frequently appearing words can be domain-specific features. In this paper, a novel Domain Feature Miner (DOMINER) approach is proposed for robust extractive summarization. The entire domain feature set mining problem is modelled as a clustering problem. Firstly, the bond energy based clustering technique is employed to cluster the domain features based on their frequency and co-appearance counts. Later, relevant clusters are extracted for the final set of domain feature set retrieval. The Proposed DOMINER scheme is extensively evaluated against quantitative performance metrics such as precision, recall, and F-score for six diversified domains such as Cellphone, Camera, Laptop, Tablet, Television, and Hotel. Experimental results on benchmark data sets reveal that proposed DOMINER scheme mines high quality of domain feature from unstructured reviews evident from precision, recall, and F-score values as 78.10%, 64.21%, and 70.48%, respectively against state of the art existing schemes. The high quality domain features extraction from DOMINER help generate the robust extractive summaries for product and services.

Interpretable extractive text summarization with meta-learning and BI-LSTM: A study of meta learning and explainability techniques

Text summarization is a widely-researched problem among scholars in the field of natural language processing. Multiple techniques have been proposed to help tackle this problem, yet some of these methodologies may still exhibit limitations such as the requirements for large training datasets, which might not always be possible, but more importantly, the lack of interpretability or transparency of the model. In this paper, we propose using meta-learning algorithm to train a deep learning model for extractive text summarization and then using various explanatory techniques such as SHAP (Shapley, 1953), linear regression (Lederer, 2022), decision trees (Fürnkranz, 2010), and input modification to gain insights into the model’s decision making process. To evaluate the effectiveness of our approach, we will compare it to other popular natural language processing models like BERT (Miller, 2019) or XLNET (Yang et al., 2020) using the ROUGE metrics (Lin, 2004). Overall, our proposed approach provides a promising solution to the limitations of existing methods and a framework for improving the explainability of deep learning models in other natural language processing tasks.

Tangent Search Long Short Term Memory with Aadaptive Reinforcement Transient Learning based Extractive and Abstractive Document Summarization

Tangent Search Long Short Term Memory with Aadaptive Reinforcement Transient Learning based Extractive and Abstractive Document Summarization

TA-Sum: The Extractive Summarization Research Based on Topic Information

<p>Text summarization is divided into extractive summarization and abstractive summarization. The extractive summarization technology aims to extract some main phrases and sentences from the original text to form a short summary for people to read quickly. However, extractive summarization is faced with problems such as poor sentence coherence and incomplete information, which makes it difficult to screen out important sentences from the source text. DNN (Deep Neural Network) is widely used for text summarization task. This paper proposes a TA-Sum model based on the neural topic model. Introducing the topic information can help people understand the relevant main content of source text quickly. We obtain the topic information using the neural topic model and implement the attention mechanism to fuse the topic information with the text representation, which improves the semantic integrity and completeness of the summary. The experimental results on the large-scale English data sets CNN/Daily mail are improved by 0.37%, 0.11%, and 0.17% respectively compared with BertSum, which demonstrates the effectiveness of our method.</p> <p> </p>

A hybrid approach for text summarization using semantic latent Dirichlet allocation and sentence concept mapping with transformer

<span lang="EN-US">Automatic text summarization generates a summary that contains sentences reflecting the essential and relevant information of the original documents. Extractive summarization requires semantic understanding, while abstractive summarization requires a better intermediate text representation. This paper proposes a hybrid approach for generating text summaries that combine extractive and abstractive methods. To improve the semantic understanding of the model, we propose two novel extractive methods: semantic latent Dirichlet allocation (semantic LDA) and sentence concept mapping. We then generate an intermediate summary by applying our proposed sentence ranking algorithm over the sentence concept mapping. This intermediate summary is input to a transformer-based abstractive model fine-tuned with a multi-head attention mechanism. Our experimental results demonstrate that the proposed hybrid model generates coherent summaries using the intermediate extractive summary covering semantics. As we increase the concepts and number of words in the summary the rouge scores are improved for precision and F1 scores in our proposed model.</span>

An Extensive Survey on Investigation Methodologies for Text Summarization

Natural language processing (NLP) is a fast-expanding field, and text summarization has recently gained a lot of research interest. The necessity for automatic summarizing approaches to effectively digest massive amounts of textual data has grown in importance, due to the plethora (excessive amount of something) of information available in the digital age [18]. By automatically producing succinct and educational summaries of extensive materials, NLP-based text summarizing systems have the potential to revolutionize the way humans consume and process information. This review paper offers a thorough examination of the text summarizing research approaches. The process of creating a concise and useful summary of a text document is called text summarization. Even for cutting-edge natural language processing (NLP) systems, it is a difficult task. It was carried out using a thorough analysis of the most recent text summarizing research. The evaluation revealed a variety of research approaches that have been employed in the creation and assessment of text summarizing systems. This study's key discovery is that there are numerous different investigative approaches that can be used for text summarizing. These methods can be roughly divided into two groups: • Extractive text summarization • Abstractive text summarization During the review we found that extractive summarization is a fairly simple method as it selects the key phrases from a text and extracts them to create a summary while abstractive summarization presents data in a clearer, more informative fashion by producing a summary. This review was important because it gives a thorough overview of the research approaches utilized for text summarizing, this article is significant. Researchers and programmers can utilize this data to create brand-new, improved text summarizing systems. [20]

Clause-aware extractive summarization with topical decoupled contrastive learning

The sentence-level extracted summary is inevitably mixed with redundant information due to the uninformative phrases or detailed expressions mixed in it. The extraction of fine-grained units is dedicated to retain the semantical integrity. To keep the balance between text redundancy and semantical integrity, we propose a novel clause-aware summarization model (TDCL-ClauseSum). We separate complex sentences into grammatically independent but semantically dependent clauses. The clause is regarded as the extraction unit and leverage graph neural network and topical information to capture clause-level relationship. Then a decoupled contrastive loss is stacked over the neural model to fill the gap between topic prediction and clause classification. The experiments of TDCL-ClauseSum are evaluated on two public benchmark datasets CNN/daily mail and New York Times, which contain 310574 and 150536 samples, respectively. Various experiments show that our method achieves remarkable performance on the two datasets (CNN/daily mail:43.94/20.65/40.75, New York Times:49.69/29.84/43.01, in ROUGE-1/ROUGE-2/ROUGE-L). Its promising performance demonstrates that the superiority of clause extraction.

Opinion Summarization via Submodular Information Measures

This paper focuses on opinion summarization for constructing subjective and concise summaries representing essential opinions of online text reviews. As previous works rarely focus on the relationship between opinions, topics, and sentences, we propose a set of new requirements for Opinion-Topic-Sentence, which are essential for performing opinion summarization. We prove that Opinion-Topic-Sentence can be theoretically analyzed by submodular information measures. Thus, our proposed method can reduce redundant information, strengthen the relevance to given topics, and informatively represent the underlying emotional variations. While conventional methods require human-labeled topics for extractive summarization, we use unsupervised topic modeling methods to generate topic features. We propose four submodular functions and two optimization algorithms with proven performance bounds that can maximize opinion summarization's utility. An automatic evaluation metric, Topic-based Opinion Variance, is also derived to compensate for ROUGE-based metrics of opinion summarization evaluation. Four large, diversified, and representative corpora, OPOSUM, Opinosis, Yelp, and Amazon reviews, are used in our study. The results on these online review texts corroborate the efficacy of our proposed metric and framework.

Decomposition–based multi-objective differential evolution for extractive multi-document automatic text summarization

The central challenge in Automatic Text Summarization (ATS) involves efficiently generating machine-generated text summaries through optimization algorithms. An ATS is a critical component for systems dealing with textual information processing. However, the current approach faces a significant hurdle due to the computational intensity of the process, particularly when employing complex optimization techniques like swarm intelligence optimization alongside a costly ATS repair operator. While the current approach yields impressive Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics for the generated summary, it struggles with inefficiencies, mainly attributed to the substantial optimization time consumed by the ATS repair operator scheme. In order to address this, a novel solution called Decomposition-based Multi-Objective Differential Evolution (MODE/D) is proposed. It is built upon the foundation of Differential Evolution for Multi-Objective Optimization (DEMO) and the weighted sum method (WS), coupled with an innovative ATS repair operator scheme. Through experimentation on Document Understanding Conferences (DUC) datasets, the novel approach of MODE/D – WS is validated by evaluating the results using ROUGE metrics. The outcomes are twofold: a remarkable reduction in serial execution time and a noteworthy enhancement over existing techniques in the scholarly domain, as evidenced by improved ROUGE-1, ROUGE-2, and ROUGE-L scores.

HTPosum:Heterogeneous Tree Structure augmented with Triplet Positions for extractive Summarization of scientific papers

Currently, many summarization models are based on Transformer architectures, which regard text as a connected graph of words and tokens, thus fail to fully leverage the text’s hierarchical structure. However, hierarchical structural information is crucial in understanding long documents, especially scientific papers. To exploit the structural information, we propose a Heterogeneous Tree structure augmented with Triplet Positions for extractive Summarization of scientific papers (HTPosum). The proposed model constructs a heterogeneous tree for each document, introducing section nodes and a global node to capture the documents’ structural information. The tree is then augmented with a novel triplet position, which consists of three values that represent the depth, parent width position, and sibling width position of each node in a tree. The triplet position provides a unified view of the document structure . Experimental results show that the proposed model achieves state-of-the-art extractive performance on the PubMed and arXiv datasets compared with the latest scientific paper summarization models.

EXABSUM: a new text summarization approach for generating extractive and abstractive summaries

Due to the exponential growth of online information, the ability to efficiently extract the most informative content and target specific information without extensive reading is becoming increasingly valuable to readers. In this paper, we present 'EXABSUM,' a novel approach to Automatic Text Summarization (ATS), capable of generating the two primary types of summaries: extractive and abstractive. We propose two distinct approaches: (1) an extractive technique (EXABSUMExtractive), which integrates statistical and semantic scoring methods to select and extract relevant, non-repetitive sentences from a text unit, and (2) an abstractive technique (EXABSUMive), which employs a word graph approach (including compression and fusion stages) and re-ranking based on keyphrases to generate abstractive summaries using the source document as an input. In the evaluation conducted on multi-domain benchmarks, EXABSUM outperformed extractive summarization methods and demonstrated competitiveness against abstractive baselines.

Development of Text Summarization Method based on Graph Theory and Malatya Centrality Algorithm

With the advancement of the internet, humanity has gained easy access to a plethora of information. However, to access accurate content, numerous texts and sources must be read. These texts often contain repetitive words and sentences. The abundance of information renders reading texts in their entirety inefficient in terms of time and makes finding suitable content challenging. To overcome these difficulties, various methods have been developed in research on automatic summarization. In the literature, there are numerous methods developed for different purposes in text summarization. Nevertheless, text summarization can generally be divided into two distinct categories: extractive and abstractive summarization. Abstractive algorithms tend to create new sentences by learning from the text. However, this approach prolongs the working process due to the learning phase and the generated sentences may not possess absolute accuracy. On the other hand, extractive methods, if unable to generate new sentences, have the ability to provide faster and completely accurate summaries by selecting sentences that already exist in the text. For these reasons, in our study, the aim is to perform text summarization using graph theory and the Malatya Centrality Algorithm. The Malatya Centrality Algorithm offers a polynomial approach to solving Vertex Cover Problems and is regarded as an effective solution method. It is believed that the Malatya Centrality Algorithm will contribute to graph-based text summarization. The implementation has been developed using the Python programming language, and the obtained results have been evaluated.

A Review of Text Summarization Techniques Using NLP

Techniques that employ natural language processing (NLP), often known as text summarizing, automatically construct summaries of extensive texts. Extractive and abstractive summarization are two main categories that may be used to classify these methods. In extractive summarizing, the most significant lines or phrases from a text are isolated and used to generate a summary. On the other hand, in abstractive summarization, a summary is generated that is clear, short, and accurate in its representation of the text's primary concepts. NLP methods like sentence segmentation, part-of-speech tagging, named entity recognition, and semantic analysis are used in generating a summary from a text and locating and extracting relevant information from the text. Text summarizing is a subject that has received a significant amount of study and has applications in various fields, including the summation of news articles, documents, and emails, among other things.

Topic model for long document extractive summarization with sentence-level features and dynamic memory unit

The Transformer-based summarization models rely solely on the attention mechanism for document encoding, making it difficult to accurately capture long-range dependencies in long documents due to the presence of attention redundancy. To address this issue, we propose an extractive summarization framework guided by a topic model (TopicSum) that utilizes a heterogeneous graph neural network to leverage the topic information as document-level features during the sentence selection process, thereby capturing the long-range dependencies among sentences. The sentence-level features in this topic model align with the basic unit of the extractive summarization task. Additionally, a memory mechanism is employed to dynamically store and update the memory module, reducing the potential of repetitive information guiding sentence selection. We evaluated the model on three large document datasets, namely Pubmed, arXiv, and GovReport, and achieved significantly higher Rouge scores than previous works, including extractive and abstractive models. Furthermore, our experiments demonstrate that recent highly regarded large language models such as ChatGPT are insufficient to handle the long document summarization task directly. The proposed approach in this paper exhibits sufficient competitiveness in terms of both generation quality and deployment conditions.

Extractive social media text summarization based on MFMMR-BertSum

The advancement of computer technology has led to an overwhelming amount of textual information, hindering the efficiency of knowledge intake. To address this issue, various text summarization techniques have been developed, including statistics, graph sorting, machine learning, and deep learning. However, the rich semantic features of text often interfere with the abstract effects and lack effective processing of redundant information. In this paper, we propose the Multi-Features Maximal Marginal Relevance BERT (MFMMR-BertSum) model for Extractive Summarization, which utilizes the pre-trained model BERT to tackle the text summarization task. The model incorporates a classification layer for extractive summarization. Additionally, the Maximal Marginal Relevance (MMR) component is utilized to remove information redundancy and optimize the summary results. The proposed method outperforms other sentence-level extractive summarization baseline methods on the CNN/DailyMail dataset, thus verifying its effectiveness.

Enhanced sentence representation for extractive text summarization: Investigating the syntactic and semantic features and their contribution to sentence scoring

Enhanced sentence representation for extractive text summarization: Investigating the syntactic and semantic features and their contribution to sentence scoring