Multi-document Summarization Research Articles

Automated multi-document summarization using extractive-abstractive approaches

This study presents a multi-document text summarizing system that employs a hybrid approach, including both extractive and abstractive methods. The goal of document summarizing is to create a coherent and comprehensive summary that captures the essential information contained in the document. The difficulty in multi-document text summarization lies in the lengthy nature of the input material and the potential for redundant information. This study utilises a combination of methods to address this issue. This study uses the TextRank algorithm as an extractor for each document to condense the input sequence. This extractor is designed to retrieve crucial sentences from each document, which are then aggregated and utilised as input for the abstractor. This study uses bidirectional and auto-regressive transformers (BART) as an abstractor. This abstractor serves to condense the primary sentences in each document into a more cohesive summary. The evaluation of this text summarizing system was conducted using the ROUGE measure. The research yields ROUGE R1 and R2 scores of 41.95 and 14.81, respectively.

Boosting multi-document summarization with hierarchical graph convolutional networks

The input of the multi-document summarization task is usually long and has high redundancy. Encoding multiple documents is a challenge for the Seq2Seq architecture. The way of concatenating multiple documents into a sequence ignores the relation between documents. Attention-based Seq2Seq architectures have slightly improved the cross-document relation modeling for multi-document summarization. However, these methods ignore the relation between sentences, and there is little improvement that can be achieved through the attention mechanism alone. This paper proposes a hierarchical approach to leveraging the relation between words, sentences, and documents for abstractive multi-document summarization. Our model employs the Graph Convolutional Networks (GCN) for capturing the cross-document and cross-sentence relations. The GCN module can enrich semantic representations by generating high-level hidden features. Our model achieves significant improvement over the attention-based baseline, beating the Hierarchical Transformer by 3.4/1.64, 1.92/1.44 ROUGE-1/2 F1 points on the Multi-News and WikiSum datasets, respectively. Experimental results demonstrate that our delivered method brings substantial improvements over several strong baselines.

GPU-accelerated extractive multi-document text summarization using decomposition-based multi-objective differential evolution

Multi-document text summarization is a computationally intensive task, mainly when employing complex optimization algorithms. The computational demands increase significantly due to integrating complex optimization algorithms and the computationally expensive repair operator. As the complexity of the optimization process grows and larger datasets are processed, execution time becomes a critical bottleneck, making real-time summarization challenging. A novel approach, decomposition-based multi-objective differential evolution (MODE/D), was introduced to address these demands in a serial execution context, but its sequential design leads to long execution times when applied to large datasets. This paper introduces the first-ever GPU-accelerated decomposition-based multi-objective differential evolution (GMODE/D), specifically designed to overcome these performance bottlenecks in optimization-based extractive multi-document text summarization. The proposed GMODE/D algorithm introduces two novel execution variants: Variant I, where the enhanced sentence scoring repair operator is executed on the CPU, and Variant II, where the sentence scoring is offloaded to the GPU to enhance performance further. These variants enable the exploration of computational models that balance CPU and GPU tasks in heterogenous environments. Experiments conducted on Document Understanding Conferences (DUC) datasets demonstrate that GMODE/D achieves a speedup of 18.17x over MODE/D and processes summaries at a rate of 215.52 words per second (WPS). Additionally, GMODE/D maintains high summary quality, achieving notable ROUGE-1, ROUGE-2, and ROUGE-L scores. The results show that GMODE/D significantly reduces execution time, setting a new benchmark in the performance of optimization-based extractive text summarization.

Multi-document Text Summarization through Features Relevance Calculation

Multi-document Text Summarization through Features Relevance Calculation

Social-sum-Mal: A Dataset for Abstractive Text Summarization in Malayalam

Abstractive text summarization techniques for Malayalam language is still in its infancy. The lack of benchmarked datasets for this task is one of the constraints in developing and testing good models. Malayalam has seven nominal case forms, two nominal number forms, and three gender forms. It is subjected to extreme agglutination and inflection. Due to this, the translation of other text summarization datasets to Malayalam may not capture these case forms effectively. Therefore curation of datasets from scratch is highly demanded for specific text-processing applications in Malayalam. This paper introduces a novel dataset designed specifically for advancing the field of automatic abstractive text summarization in Malayalam language. The dataset is curated to address the unique linguistic characteristics of the Malayalam language. It is named as Social-sum-Mal dataset, capable of addressing three different types of summarization tasks- long, extreme, and query-based summarizations. In addition, Social-sum-Mal can be extended for other applications like text classification, multi-document summarization, and question answering. To enhance the dataset transparency, a datasheet is created for Social-sum-Mal. Data accuracy and annotator biases are evaluated using proper testing strategies including Jaccard, cosine, and overlap similarities. The correctness of the dataset is further evaluated by comparing it with a deep-learning-based text summarization model.

AraTSum: Arabic Twitter Trend Summarization Using Topic Analysis and Extractive Algorithms

Twitter’s trending topics enable users to view the topics currently being discussed on the platform. Users can stay up to date with news, events, and conversations. However, the platform’s method of sorting tweets by time can make it hard to gather semantic information. To fully comprehend the various dimensions of trends and the diverse opinions surrounding them, users need to sift through a substantial number of results. Traditional techniques for content summarization, such as multi-document summarization, can facilitate information aggregation, categorization, and visualization of events, but there are two challenges. First, they fail to consider the topic’s polarity, which is essential to covering all aspects of the subject and incorporating less popular opinions. Second, some techniques only provide summaries at the topic level, potentially leaving out crucial dimensions that require representation in this summary. This research developed a novel summarization approach on Twitter which is known as ARAbic Trending SUMmarization (AraTSum). The proposed system generates the summary based on the extracted topics and aspects from the trend. The approach involves a topic sentiment-based technique that combines generative statistical Latent Dirichlet Allocation with a pre-trained model to automatically reflect the sentiments (negative or positive) of tweets in each topic; followed by extractive summarization algorithms in each cluster. The AraTSum was evaluated through several experiments on five different X datasets. The obtained results showed that AraTSum outperformed existing approaches on the ROUGE evaluation metric compared to state-of-the-art Twitter event summarizing algorithms. To ensure a comprehensive and accurate evaluation, three human experts were tasked with manually summarizing the utilized five datasets. The results demonstrated that the proposed AraTSum method is dependent on sentiment topical aspect analysis, and it enhances the summarization's performance.

An indicator-based multi-objective variable neighborhood search approach for query-focused summarization

Currently, automatic multi-document summarization is an interesting subject in numerous fields of study. As a part of it, query-focused summarization is becoming increasingly important in recent times. These methods can automatically produce a summary based on a query given by the user, including the most relevant information from the query at the same time as the redundancy among sentences is reduced. This can be achieved by developing and applying a multi-objective optimization approach. In this paper, an Indicator-based Multi-Objective Variable Neighborhood Search (IMOVNS) algorithm has been designed, implemented, and tested for the query-focused extractive multi-document summarization problem. Experiments have been carried out with datasets from Text Analysis Conference (TAC). The results were evaluated using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics. IMOVNS has greatly improved the results presented in the scientific literature, providing improvement percentages in ROUGE metric reaching up to 69.24% in ROUGE-1, up to 57.70% in ROUGE-2, and up to 77.37% in ROUGE-SU4 scores. Hence, the proposed IMOVNS offers a promising solution to the query-focused summarization problem, thus highlighting its efficacy and potential for enhancing automatic summarization techniques.

Modified CNN with Transfer Learning for Multi-Document Summarization: Proposing Co-Occurrence Matrix Generation-Based Knowledge Extraction

Modified CNN with Transfer Learning for Multi-Document Summarization: Proposing Co-Occurrence Matrix Generation-Based Knowledge Extraction

3A-COT: an attend-arrange-abstract chain-of-thought for multi-document summarization

3A-COT: an attend-arrange-abstract chain-of-thought for multi-document summarization

Multi-document hybrid text summarization with bi-LSTM RNN for Telugu language

Multi-document hybrid text summarization with bi-LSTM RNN for Telugu language

Over comparative study of text summarization techniques based on graph neural networks

Due to the enormous content of text available online through emails, social media, and news articles, it has become complicated to summarize the textual information from multiple documents. Text summarization automatically creates a comprehensive description of the document that retains its informative contents through the keywords, where Multi-Document Summarization (MDS) is a productive tool for data accumulation that creates a concise and informative summary from the documents. In order to extract the relevant information from the documents, Graph neural networks (GNNs) is the neural structure that detains the interrelation of the graph by progressing the messages between the graphical nodes. In the current years, the advanced version of GNNs, such as graph attention network (GAN), graph recurrent network, and graph convolutional network (GCN) provides a remarkable performance in text summarization with the advantage of deep learning techniques. Hence, in this survey, graph approaches for text summarization has been analyzed and discussed, where the recent text summarization model based on Deep learning techniques are highlighted. Further, the article provides the taxonomy to abstract the design pattern of Neural Networks and conducts a comprehensive of the existing text summarization model. Finally, the review article enlists the future direction of the researcher, which would motivate the enthusiastic and novel contributions in text summarizations.

Advancements in Text Summarization Through Machine Learning: A Comprehensive Survey and Analysis

Due to the extensive amount of text available for any given task, for instance, a research project, it has become a need to have the gist of these documents in a succinct format. In this review paper, we discussed various methods used for single and multi-document summarization. It explores extractive, abstractive, and hybrid methods, along with the role of deep learning models like RNNs, CNNs, and transformers. The survey examines datasets, evaluation metrics, recent advancements, and future scopes in this field. A comparative analysis of methodologies and approaches is also presented.

QuerySum: A Multi-Document Query-Focused Summarization Dataset Augmented with Similar Query Clusters

Query-focused summarization (QFS) aims to summarize the source document(s) with regard to a specific aspect of information given in a query. It plays an important role in presenting users with a concise answer summary from a set of query-relevant documents retrieved by the information retrieval system. Nonetheless, the QFS research has long been hampered by the lack of adequate datasets in terms of both quality and quantity. In this paper, we introduce a large-scale multi-document query-focused summarization dataset, called QuerySum, which contains 27,041 data samples covering diverse topics and its quality is guaranteed through human verification. Unlike some previous QFS datasets constructed directly from the question answering datasets, 74% queries in our dataset are the challenging non-factoid What-, Why-, and How- questions. More importantly, we also provide a set of similar queries together with the corresponding summaries pairs for each query as the retrieved context, presenting a new feature of QuerySum. We aim to encourage research efforts in query intention understanding in the context of QFS. Leveraging QuerySum's depth, we propose a model for query-aware multi-document summarization and set a new QFS benchmark.

Key point generation as an instrument for generating core statements of a political debate on Twitter.

Identifying key statements in large volumes of short, user-generated texts is essential for decision-makers to quickly grasp their key content. To address this need, this research introduces a novel abstractive key point generation (KPG) approach applicable to unlabeled text corpora, using an unsupervised approach, a feature not yet seen in existing abstractive KPG methods. The proposed method uniquely combines topic modeling for unsupervised data space segmentation with abstractive summarization techniques to efficiently generate semantically representative key points from text collections. This is further enhanced by hyperparameter tuning to optimize both the topic modeling and abstractive summarization processes. The hyperparameter tuning of the topic modeling aims at making the cluster assignment more deterministic as the probabilistic nature of the process would otherwise lead to high variability in the output. The abstractive summarization process is optimized using a Davies-Bouldin Index specifically adapted to this use case, so that the generated key points more accurately reflect the characteristic properties of this cluster. In addition, our research recommends an automated evaluation that provides a quantitative complement to the traditional qualitative analysis of KPG. This method regards KPG as a specialized form of Multidocument summarization (MDS) and employs both word-based and word-embedding-based metrics for evaluation. These criteria allow for a comprehensive and nuanced analysis of the KPG output. Demonstrated through application to a political debate on Twitter, the versatility of this approach extends to various domains, such as product review analysis and survey evaluation. This research not only paves the way for innovative development in abstractive KPG methods but also sets a benchmark for their evaluation.

From coarse to fine: Enhancing multi-document summarization with multi-granularity relationship-based extractor

Multi-Document Summarization (MDS) is a challenging task due to the fact that multiple documents not only have extremely long inputs but may also be overlapping, complementary, or contradictory to each other. In this paper, we propose to capture complex cross-document interactions to handle lengthy inputs for better multi-document summarization. Specifically, we present MDS-MGRE, a coarse-to-fine MDS framework that introduces Multi-Granularity Relationships into an Extract-then-summarize pipeline. In the coarse-grained stage, multi-granularity embedding, heterogeneous graph construction, and MGRExtractor work together to convert redundant multi-documents into compact meta-documents. We first utilize pre-trained language model BERT to obtain semantically rich embeddings for documents at different granularities, including documents, paragraphs, sentence-sets, and sentences. Then, we construct a heterogeneous graph with 4 types of nodes (document nodes, paragraph nodes, sentence-set nodes, and sentence nodes) and corresponding connecting edges to model rich document relationships. Furthermore, we propose a novel Multi-Granularity Relationship-based Extractor (MGRExtractor) to produce meta-documents by efficiently pruning heterogeneous graphs. More precisely, it consists of 4 main modules: noise removal, redundancy removal, multi-granularity scoring, and sentence-set selection. In the fine-grained stage, we employ the large configuration of BART as our abstractive summarizer to generate system summaries from the extracted meta-documents. Experimental results on two benchmark datasets show that our framework significantly outperforms strong baselines with comparable parameters, and slightly underperforms methods with a maximum encoding length of 16,384 tokens. For Multi-News and WCEP, automatic evaluation results show that MDS-MGRE achieves an average performance improvement of 1.75% and 8.77% compared to the state-of-the-art systems with comparable parameters, respectively. Such positive results demonstrate the benefits of generating high-quality meta-documents to enhance MDS by modeling rich document relationships.

TOMDS (Topic-Oriented Multi-Document Summarization): Enabling Personalized Customization of Multi-Document Summaries

In a multi-document summarization task, if the user can decide on the summary topic, the generated summary can better align with the reader’s specific needs and preferences. This paper addresses the issue of overly general content generation by common multi-document summarization models and proposes a topic-oriented multi-document summarization (TOMDS) approach. The method is divided into two stages: extraction and abstraction. During the extractive stage, it primarily identifies and retrieves paragraphs relevant to the designated topic, subsequently sorting them based on their relevance to the topic and forming an initial subset of documents. In the abstractive stage, building upon the transformer architecture, the process includes two parts: encoding and decoding. In the encoding part, we integrated an external discourse parsing module that focuses on both micro-level within-paragraph semantic relationships and macro-level inter-paragraph connections, effectively combining these with the implicit relationships in the source document to produce more enriched semantic features. In the decoding part, we incorporated a topic-aware attention mechanism that dynamically zeroes in on information pertinent to the chosen topic, thus guiding the summary generation process more effectively. The proposed model was primarily evaluated using the standard text summary dataset WikiSum. The experimental results show that our model significantly enhanced the thematic relevance and flexibility of the summaries and improved the accuracy of grammatical and semantic comprehension in the generated summaries.

Chain-of-event prompting for multi-document summarization by large language models

PurposeIn the era of big data, various industries are generating large amounts of text data every day. Simplifying and summarizing these data can effectively serve users and improve efficiency. Recently, zero-shot prompting in large language models (LLMs) has demonstrated remarkable performance on various language tasks. However, generating a very “concise” multi-document summary is a difficult task for it. When conciseness is specified in the zero-shot prompting, the generated multi-document summary still contains some unimportant information, even with the few-shot prompting. This paper aims to propose a LLMs prompting for multi-document summarization task.Design/methodology/approachTo overcome this challenge, the authors propose chain-of-event (CoE) prompting for multi-document summarization (MDS) task. In this prompting, the authors take events as the center and propose a four-step summary reasoning process: specific event extraction; event abstraction and generalization; common event statistics; and summary generation. To further improve the performance of LLMs, the authors extend CoE prompting with the example of summary reasoning.FindingsSummaries generated by CoE prompting are more abstractive, concise and accurate. The authors evaluate the authors’ proposed prompting on two data sets. The experimental results over ChatGLM2-6b show that the authors’ proposed CoE prompting consistently outperforms other typical promptings across all data sets.Originality/valueThis paper proposes CoE prompting to solve MDS tasks by the LLMs. CoE prompting can not only identify the key events but also ensure the conciseness of the summary. By this method, users can access the most relevant and important information quickly, improving their decision-making processes.

A deep learning framework for multi-document summarization using LSTM with improved Dingo Optimizer (IDO)

A deep learning framework for multi-document summarization using LSTM with improved Dingo Optimizer (IDO)

A knowledge-graph based text summarization scheme for mobile edge computing

As the demand for edge services intensifies, text, being the most common type of data, has seen a significant expansion in data volume and an escalation in processing complexity. Furthermore, mobile edge computing (MEC) service systems often faces challenges such as limited computational capabilities and difficulties in data integration, requiring the development and implementation of more efficient and lightweight methodologies for text data processing. To swiftly extract and analysis vital information from MEC text data, an automatic generation scheme of multi-document text summarization based on knowledge graph is proposed in this paper, named KGCPN. For the text data from MEC devices and applications, the natural language processing technology is used to execute the data pre-processing steps, which transforms the MEC text data into a computationally tractable and semantically comprehensible format. Then, the knowledge graph of multi-document text is constructed by integrating the relationship paths and entity descriptions. The nodes and edges of the knowledge graph serve to symbolize the semantic relationships within the text, and the Graph Convolution Neural network (GCN) is used to understand the text and learn the semantic representation. Finally, a pointer-generator network model accepts the encoding information from GCN and automatically generate a general text summarization. The experimental results indicate that our scheme can effectively facilitate the smart pre-processing and integration of MEC data.

Mining Both Commonality and Specificity From Multiple Documents for Multi-Document Summarization

Mining Both Commonality and Specificity From Multiple Documents for Multi-Document Summarization