Search

Extractive summarization, a pivotal task in natural language processing, aims to distill essential content from lengthy documents efficiently. Traditional methods often struggle with capturing the nuanced interdependencies between different document elements, which is crucial to producing coherent and contextually rich summaries. This paper introduces Multi-Element Contextual Hypergraph Extractive Summarizer (MCHES), a novel framework designed to address these challenges through an advanced hypergraph-based approach. MCHES constructs a contextual hypergraph where sentences form nodes interconnected by multiple types of hyperedges, including semantic, narrative, and discourse hyperedges. This structure captures complex relationships and maintains narrative flow, enhancing semantic coherence across the summary. The framework incorporates a Contextual Homogenization Module (CHM), which harmonizes features from diverse hyperedges, and a Hypergraph Contextual Attention Module (HCA), which employs a dual-level attention mechanism to focus on the most salient information. The innovative Extractive Read-out Strategy selects the optimal set of sentences to compose the final summary, ensuring that the latter reflects the core themes and logical structure of the original text. Our extensive evaluations demonstrate significant improvements over existing methods. Specifically, MCHES achieves an average ROUGE-1 score of 44.756, a ROUGE-2 score of 24.963, and a ROUGE-L score of 42.477 on the CNN/DailyMail dataset, surpassing the best-performing baseline by 3.662%, 3.395%, and 2.166% respectively. Furthermore, MCHES achieves BERTScore values of 59.995 on CNN/DailyMail, 88.424 on XSum, and 89.285 on PubMed, indicating superior semantic alignment with human-generated summaries. Additionally, MCHES achieves MoverScore values of 87.432 on CNN/DailyMail, 60.549 on XSum, and 59.739 on PubMed, highlighting its effectiveness in maintaining content movement and ordering. These results confirm that the MCHES framework sets a new standard for extractive summarization by leveraging contextual hypergraphs for better narrative and thematic fidelity. [ABSTRACT FROM AUTHOR]

Abstractive summarization (AS) aims to generate more flexible and informative descriptions than extractive summarization. Nevertheless, it often distorts or fabricates facts in the original article. To address this problem, some existing approaches attempt to evaluate or verify factual consistency, or design models to reduce factual errors. However, most of the efforts either have limited effects or result in lower rouge scores while reducing factual errors. In other words, it is challenging to promote factual consistency while maintaining the informativeness of generated summaries. Inspired by the knowledge graph embedding technique, in this paper, we propose a novel cross-modal knowledge guided model (CKGM) for AS, which embeds a multimodal knowledge graph (MKG) combining image entity-relationship information and textual factual information (FI) into BERT to accomplish cross-modal information interaction and knowledge expansion. The pre-training method obtains rich contextual semantic information, while the knowledge graph supplements the textual information. In addition, an entity memory embedding algorithm is further proposed to improve information fusion efficiency and model training speed. We elaborately conducted ablation experiments and evaluated our model on the Visual Genome, FewRel, MSCOCO, and CNN/DailyMail datasets. Experimental results demonstrate that our model can significantly improve the FI consistency and informativeness of generated summaries. [ABSTRACT FROM AUTHOR]

In the current digital epoch, the vast expanse of information has revolutionized the accessibility of knowledge and perspectives. Nevertheless, this information abundance has introduced challenges in navigating and comprehending the deluge of textual data. The surge in online news articles, research papers, reports, and diverse document genres has accentuated the necessity for proficient document summarization techniques. Traditional manual methods of summarization are time-intensive and influenced by subjective biases. In contrast, the synergy between Natural Language Processing (NLP) and machine learning has unlocked the potential for automated document summarization, promising efficient information consumption and informed decision-making. This research paper delves into the convergence of these factors. It is driven by the Longformer model's distinctive capability to manage extensive texts while retaining contextual coherence--a potential solution to the hurdle of large document summarization. By capitalizing on the Longformer's architecture, this study endeavors to exploit its prowess in generating cohesive summaries from lengthy source documents, thereby amplifying the accessibility of intricate information. [ABSTRACT FROM AUTHOR]

The need for automatic text summarization is natural: there is a huge volume of information available online, which prompts for a widespread interest in extracting relevant information in a concise and understandable manner. Here, automated text summarization has been treated as an extractive single-document summarization problem in the proposed system. To solve this problem, a particle swarm optimisation (PSO) algorithm-based approach is suggested, with the goal of producing good summaries in terms of content coverage, informativeness, and readability. This paper introduces XSumm-PSO: a new approach based on PSO optimization technique in a supervised manner for extractive summarization. Further, this paper also contributes a new feature "incorrect word" that captures misspelled words in the candidate sentences. This feature is combined with nine existing features used by proposed model to generate error free summaries. As a result, the proposed XSumm-PSO framework produces superior performance achieving improvements of +2.7%, +0.8%, and +0.8% for ROUGE-1, ROUGE-2, and ROUGE-L scores, respectively, on DUC 2002 dataset, over state-of-the-art techniques. The corresponding improvements on the CNN/DailyMail dataset are +0.97%, +0.25%, and +0.49%. We also performed sample t-test, showing the proposed approach is statistically consistent across various runs. • A PSO-based technique optimized in a supervised manner using ROGUE-1 is proposed. • The suggested model solves a single-document extractive text summarization task. • A new feature "incorrect word" is also introduced in this work. • We evaluate our proposed model on DUC-2002 and CNN/DailyMail benchmark datasets. • The suggested model generalizes better and produces better accuracy than SOTA. [ABSTRACT FROM AUTHOR]

With an increasing number of new summarization systems proposed in recent years, an automatic text evaluation metric that can accurately and reliably rate the performance of summarization systems has been a pressing need. However, current automatic text evaluation metrics can only measure one or certain aspects of the quality between two summary texts and do not agree with human judgments consistently. In this paper, we show that combining multiple well-chosen evaluation metrics and training predictive models using human annotated datasets can lead to more reliable evaluation scores than using any individual automatic metric. Our predictive models trained on a human annotated subset of the CNN/DailyMail corpus demonstrate significant improvements (e.g. approximately 25% along coherence dimension) over selected individual metrics. Furthermore, a concise meta-evaluation on automatic metrics is provided along with an analysis of the performance of 12 predictive models. We also investigate the sensitivity of automatic metrics when mixed together for training these models. We have made the code, the instructions for experiment setup, and the trained models available as a tool for comparing and evaluating text summarization systems. a https://github.com/bzhao2718/ReliableSummEvalReg. [ABSTRACT FROM AUTHOR]

Summary: News image captioning aims to generate captions or descriptions for news images automatically, serving as draft captions for creating news image captions manually. News image captions are different from generic captions as news image captions contain more detailed information such as entity names and events. Therefore, both images on news and the accompanying text are the source of generating caption of news image. Pointer‐generator network is a neural method defined for text summarization. This article proposes the Multimodal pointer‐generation network by incorporating visual information into the original network for news image captioning. The multimodal attention mechanism is proposed by splitting attention into visual attention paid to the image and textual attention paid to the text. The multimodal pointer mechanism is proposed by using both textual attention and visual attention to compute pointer distributions, where visual attention is first transformed into textual attention via the word‐image relationships. The multimodal coverage mechanism is defined to reduce repetitions of attentions or repetitions of pointer distributions. Experiments on the DailyMail test dataset and the out‐of‐domain BBC test dataset show that the proposed model outperforms the original pointer‐generator network, the generic image captioning method, the extractive news image captioning method, and the LDA‐based method according BLEU, METEOR, and ROUGL‐L evaluations. Experiments also show that the proposed multimodal coverage mechanisms can improve the model, and that transforming visual attention to pointer distributions can improve the model. [ABSTRACT FROM AUTHOR]

Neural sequence-to-sequence models are the state-of-the-art approach used in abstractive summarization of textual documents, useful for producing condensed versions of source text narratives without being restricted to using only words from the original text. Despite the advances in abstractive summarization, custom generation of summaries (e.g., towards a user’s preference) remains unexplored. In this article, we present CATS, an abstractive neural summarization model that summarizes content in a sequence-to-sequence fashion while also introducing a new mechanism to control the underlying latent topic distribution of the produced summaries. We empirically illustrate the efficacy of our model in producing customized summaries and present findings that facilitate the design of such systems. We use the well-known CNN/DailyMail dataset to evaluate our model. Furthermore, we present a transfer-learning method and demonstrate the effectiveness of our approach in a low resource setting, i.e., abstractive summarization of meetings minutes, where combining the main available meetings’ transcripts datasets, AMI and International Computer Science Institute(ICSI), results in merely a few hundred training documents. [ABSTRACT FROM AUTHOR]

In this paper, we propose DeepSumm, a novel method based on topic modeling and word embeddings for the extractive summarization of single documents. Recent summarization methods based on sequence networks fail to capture the long range semantics of the document which are encapsulated in the topic vectors of the document. In DeepSumm, our aim is to utilize the latent information in the document estimated via topic vectors and sequence networks to improve the quality and accuracy of the summarized text. Each sentence is encoded through two different recurrent neural networks based on probabilistic topic distributions and word embeddings, and then a sequence to sequence network is applied to each sentence encoding. The outputs of the encoder and the decoder in the sequence to sequence networks are combined after weighting using an attention mechanism and converted into a score through a multi-layer perceptron network. We refer to the score obtained through the topic model as Sentence Topic Score (STS) and to the score generated through word embeddings as Sentence Content Score (SCS). In addition, we propose Sentence Novelty Score (SNS) and Sentence Position Score (SPS) and perform a weighted fusion of the four scores for each sentence in the document to compute a Final Sentence Score (FSS). The proposed DeepSumm framework was evaluated on the standard DUC 2002 benchmark and CNN/DailyMail datasets. Experimentally, it was demonstrated that our method captures both the global and the local semantic information of the document and essentially outperforms existing state-of-the-art approaches for extractive text summarization with ROUGE-1, ROUGE-2, and ROUGE-L scores of 53.2, 28.7 and 49.2 on DUC 2002 and 43.3, 19.0 and 38.9 on CNN/DailyMail dataset. • DeepSumm for extractive summarization based on seq2seq networks. • Sentence encoded with probabilistic topic distributions and word embeddings RNNs. • Proposed Sentence Novelty Score, based on sentence content and topic embeddings. • Seq2seq attention networks extract content and topic Scores. • Summary generated using four sentence scores: Content, Topic, Novelty and Position. [ABSTRACT FROM AUTHOR]

Select-then-compress is a popular hybrid, framework for text summarization due to its high efficiency. This framework first selects salient sentences and then independently condenses each of the selected sentences into a concise version. However, compressing sentences separately ignores the context information of the document, and is therefore prone to delete salient information. To address this limitation, we propose a novel condense-then-select framework for text summarization. Our framework first concurrently condenses each document sentence. Original document sentences and their compressed versions then become the candidates for extraction. Finally, an extractor utilizes the context information of the document to select candidates and assembles them into a summary. If salient information is deleted during condensing, the extractor can select an original sentence to retain the information. Thus, our framework helps to avoid the loss of salient information, while preserving the high efficiency of sentence-level compression. Experiment results 1 1 Code will be available at https://github.com/kenchan0226/abs-then-ext-public. on the CNN/DailyMail, DUC-2002, and Pubmed datasets demonstrate that our framework outperforms the select-then-compress framework and other strong baselines. [ABSTRACT FROM AUTHOR]