Search

A large language model (LLM) is an artificial intelligence (AI) model that uses natural language processing (NLP) to understand, interpret, and generate human-like language responses from unstructured text input. Its real-time response capabilities and eloquent dialogue enhance the interactive user experience in human–AI communication like never before. By gathering several sources on the internet, LLM chatbots can interact and respond to a wide range of queries, including problem solving, text summarization, and creating informative notes. Since ophthalmology is one of the medical fields integrating image analysis, telemedicine, AI, and other technologies, LLMs are likely to play an important role in eye care in the near future. This review summarizes the performance and potential applicability of LLMs in ophthalmology according to currently available publications. [ABSTRACT FROM AUTHOR]

It is important for abstractive summarization models to understand the important parts of the original document and create a natural summary accordingly. Recently, studies have been conducted to incorporate important parts of the original document during learning and have shown good performance. However, these studies are effective for explicit datasets but not implicit datasets which are relatively more abstract. This study addresses the challenge of summarizing implicit datasets, which have a lower deviation in the significance of important sentences compared to explicit datasets. A multi-task learning approach that reflects information about salient and incidental objects during the learning process was proposed. This was achieved by adding a contrastive objective to the fine-tuning process of the encoder-decoder language model. The salient and incidental parts were selected based on the ROUGE-L F1 score and their relationships were learned through triplet loss. The proposed method was evaluated using five benchmark summarization datasets, including two explicit and three implicit. The experimental results showed a greater improvement in implicit datasets, particularly for the highly abstractive XSum dataset, compared to the vanilla fine-tuning method in both the BART-base and T5-small models. [ABSTRACT FROM AUTHOR]

In the pharmaceutical industry, there is an abundance of regulatory documents used to understand the current regulatory landscape and proactively make project decisions. Due to the size of these documents, it is helpful for project teams to have informative summaries. We propose a novel solution, MedicoVerse, to summarize such documents using advanced machine learning techniques. MedicoVerse uses a multi-stage approach, combining word embeddings using the SapBERT model on regulatory documents. These embeddings are put through a critical hierarchical agglomerative clustering step, and the clusters are organized through a custom data structure. Each cluster is summarized using the bart-large-cnn-samsum model, and each summary is merged to create a comprehensive summary of the original document. We compare MedicoVerse results with established models T5, Google Pegasus, Facebook BART, and large language models such as Mixtral 8 × 7b instruct, GPT 3.5, and Llama-2-70b by introducing a scoring system that considers four factors: ROUGE score, BERTScore, business entities and the Flesch Reading Ease. Our results show that MedicoVerse outperforms the compared models, thus producing informative summaries of large regulatory documents. [ABSTRACT FROM AUTHOR]

A vast amount of textual information on the internet has amplified the importance of text summarization models. Abstractive summarization generates original words and sentences that may not exist in the source document to be summarized. Such abstractive models may suffer from shortcomings such as linguistic acceptability and hallucinations. Recall-Oriented Understudy for Gisting Evaluation (ROUGE) is a metric commonly used to evaluate abstractive summarization models. However, due to its n-gram-based approach, it ignores several critical linguistic aspects. In this work, we propose Similarity, Entailment, and Acceptability Score (SEAScore), an automatic evaluation metric for evaluating abstractive text summarization models using the power of state-of-the-art pre-trained language models. SEAScore comprises three language models (LMs) that extract meaningful linguistic features from candidate and reference summaries and a weighted sum aggregator that computes an evaluation score. Experimental results show that our LM-based SEAScore metric correlates better with human judgment than standard evaluation metrics such as ROUGE-N and BERTScore. [ABSTRACT FROM AUTHOR]

Automatic detection of prerequisite relations between concepts in education has always been a challenging AI task for researchers. Identification of prerequisite relations enables students to study new subjects more effectively and systematically, while allowing instructors to better tailor their learning materials to students' needs. However, to accurately detect these relations, the AI system must understand the context and meaning behind each concept and how it relates to other concepts in the domain. This requires a deep understanding of the educational curriculum and the ability to analyze large amounts of text and data. Large language models (LLMs) are a recent innovation in AI. LLMs have the capability to understand and generate human-like text since they are trained on a vast amount of text from the internet, books, articles, and more. LLMs can also be fine-tuned to specialize in tasks such as document summarization, question answering, or detecting user sentiment in reviews. Fine-tuning is done with a smaller, task-specific dataset. In this work, we introduce strategies for fine-tuning LLMs to improve their capability to detect prerequisite relations between educational concepts. To the best of our knowledge, this is the first work that utilizes fine-tuned LLMs for prerequisite detection. Our evaluation results demonstrate that fine-tuned LLMs are effective models for prerequisite detection. Our fine-tuning process also facilitates the generation of explanations to shed light on the reasoning behind prerequisite relations. Datasets we generated and used in fine-tuning are made public for the research community. We hope our contributions can aid in organizing and presenting knowledge in education and serve as a foundation for future research in the field. [ABSTRACT FROM AUTHOR]

The object of the research is the task of automatic abstracting of natural language texts. The importance of these tasks is determined by the existing problem of creating essays that would adequately reflect the content of the original text and highlight key information. This task requires the ability of models to deeply analyze the context of the text, which complicates the abstracting process. Results are presented that demonstrate the effectiveness of using generative models based on neural networks, text semantic analysis methods, and deep learning for automatic creation of abstracts. The use of models showed a high level of adequacy and informativeness of abstracts. GPT (Generative Pre-trained Transformer) generates text that looks like it was written by a human, which makes it useful for automatic essay generation. For example, the GPT model generates abbreviated summaries based on input text, while the BERT model is used for summarizing texts in many areas, including search engines and natural language processing. This allows for short but informative abstracts that retain the essential content of the original and provides the ability to produce high-quality abstracts that can be used for abstracting web pages, emails, social media, and other content. Compared to traditional abstracting methods, artificial intelligence provides such advantages as greater accuracy, informativeness and the ability to process large volumes of text more efficiently, which facilitates access to information and improves productivity in text processing. Automatic abstracting of texts using artificial intelligence models allows to significantly reduce the time required for the analysis of large volumes of textual information. This is especially important in today’s information environment, where the amount of available data is constantly growing. The use of these models promotes efficient use of resources and increases overall productivity in a variety of fields, including scientific research, education, business and media [ABSTRACT FROM AUTHOR]

The widespread use of the internet today, along with the rapidly increasing information, has brought along great information pollution. it has become a big problem for internet users to obtain meaningful data from this large and noisy data. Text summarization, which is generally used on texts obtained from digital media, has also been used for summarizing scientific articles in different fields. in this study, a scientific text summary study was carried out to be used on Turkish articles written in the field of informatics. A large Turkish Informatics Literature dataset was created with the articles collected from Dergipark. in addition to the text pre-processing studies available in the literature on this dataset, a new original pre-processing function has been developed by the scientific article format. While summarizing, Deep Belief Networks (DBN), which has an increasing use in the field of natural language processing in the literature, has been used. To measure the performance of the developed system, reference summaries were created with the BERT algorithm, which is a pre-trained natural language processing model. After the scientific articles were summarized with BERT and Deep Belief Networks, the abstracts were compared with BERT Score and BART Score, a specialized comparison metric of the BERT Model. The results showed that the developed Turkish informatics Literature Summarization Method constitutes a summary of a scientific article with 0.78 F-Score and 0.68 BART Score in the BERT Score metric. [ABSTRACT FROM AUTHOR]

Fine-tuning a pre-trained sequence-to-sequence-based language model has significantly advanced the field of abstractive summarization. However, the early models of abstractive summarization were limited by the gap between training and inference, and they did not fully utilize the potential of the language model. Recent studies have introduced a two-stage framework that allows the second-stage model to re-rank the candidate summary generated by the first-stage model, to resolve these limitations. In this study, we point out that the supervision method performed in the existing re-ranking model of the two-stage abstractive summarization framework cannot learn detailed and complex information of the data. In addition, we present the problem of positional bias in the existing encoder–decoder-based re-ranking model. To address these two limitations, this study proposes a hierarchical supervision method that jointly performs summary and sentence-level supervision. For sentence-level supervision, we designed two sentence-level loss functions: intra- and inter-intra-sentence ranking losses. Compared to the existing abstractive summarization model, the proposed method exhibited a performance improvement for both the CNN/DM and XSum datasets. The proposed model outperformed the baseline model under a few-shot setting. [ABSTRACT FROM AUTHOR]

Text summarization (TS) plays a crucial role in natural language processing (NLP) by automatically condensing and capturing key information from text documents. Its significance extends to diverse fields, including engineering, healthcare, and others, where it offers substantial time and resource savings. However, manual summarization is a laborious task, prompting the need for automated text summarization systems. In this paper, we propose a novel strategy for extractive summarization that leverages a generative adversarial network (GAN)-based method and Bidirectional Encoder Representations from Transformers (BERT) word embedding. BERT, a transformer-based architecture, processes sentence bidirectionally, considering both preceding and following words. This contextual understanding empowers BERT to generate word representations that carry a deeper meaning and accurately reflect their usage within specific contexts. Our method adopts a generator and discriminator within the GAN framework. The generator assesses the likelihood of each sentence in the summary while the discriminator evaluates the generated summary. To extract meaningful features in parallel, we introduce three dilated convolution layers in the generator and discriminator. Dilated convolution allows for capturing a larger context and incorporating long-range dependencies. By introducing gaps between filter weights, dilated convolution expands the receptive field, enabling the model to consider a broader context of words. To encourage the generator to explore diverse sentence combinations that lead to high-quality summaries, we introduce various noises to each document within our proposed GAN. This approach allows the generator to learn from a range of sentence permutations and select the most suitable ones. We evaluate the performance of our proposed model using the CNN/Daily Mail dataset. The results, measured using the ROUGE metric, demonstrate the superiority of our approach compared to other tested methods. This confirms the effectiveness of our GAN-based strategy, which integrates dilated convolution layers, BERT word embedding, and a generator-discriminator framework in achieving enhanced extractive summarization performance. [ABSTRACT FROM AUTHOR]

Recently, large pretrained language models (PLMs) have led a revolution in the information retrieval community. In most PLMs‐based retrieval frameworks, the ranking performance broadly depends on the model structure and the semantic complexity of the input text. Sequence‐to‐sequence generative models for question answering or text generation have proven to be competitive, so we wonder whether these models can improve ranking effectiveness by enhancing input semantics. This article introduces SE‐BERT, a semantically enhanced bidirectional encoder representation from transformers (BERT) based ranking framework that captures more semantic information by modifying the input text. SE‐BERT utilizes a pretrained generative language model to summarize both sides of the candidate passage and concatenate them into a new input sequence, allowing BERT to acquire more semantic information within the constraints of the input sequence's length. Experimental results from two Text Retrieval Conference datasets demonstrate that our approach's effectiveness increasing as the length of the input text increases. [ABSTRACT FROM AUTHOR]

The article titled "Timely need for navigating the potential and downsides of LLMs in healthcare and biomedicine" provides a comprehensive exploration of the opportunities and challenges associated with large language models (LLMs) in the field of biomedicine and healthcare. The authors discuss the transformative potential of LLMs in areas such as biomedical information retrieval, question answering, medical text summarization, information extraction, and medical education. They also highlight the need for caution regarding data privacy, ethical considerations, and the mitigation of biases. The article presents a list of popular LLMs in the health domain and identifies limitations and new challenges, along with mitigation strategies. Additionally, it suggests various applications of LLMs in healthcare, including personalized treatment recommendations, predictive health analytics, and automated medical literature review. The authors emphasize the importance of proceeding with ethical principles, inclusivity, and collaboration in integrating LLMs into healthcare. While the article provides valuable insights, it could have further explored futuristic challenges and applications of LLMs in the biomedical domain. Overall, this work contributes to the ongoing discourse on the role of AI in healthcare and sets the stage for future research and development in this field. [Extracted from the article]

ChatGPT has drawn considerable attention from both the general public and domain experts with its remarkable text generation capabilities. This has subsequently led to the emergence of diverse applications in the field of biomedicine and health. In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health. Specifically, we explore the areas of biomedical information retrieval, question answering, medical text summarization, information extraction and medical education and investigate whether LLMs possess the transformative power to revolutionize these tasks or whether the distinct complexities of biomedical domain presents unique challenges. Following an extensive literature survey, we find that significant advances have been made in the field of text generation tasks, surpassing the previous state-of-the-art methods. For other applications, the advances have been modest. Overall, LLMs have not yet revolutionized biomedicine, but recent rapid progress indicates that such methods hold great potential to provide valuable means for accelerating discovery and improving health. We also find that the use of LLMs, like ChatGPT, in the fields of biomedicine and health entails various risks and challenges, including fabricated information in its generated responses, as well as legal and privacy concerns associated with sensitive patient data. We believe this survey can provide a comprehensive and timely overview to biomedical researchers and healthcare practitioners on the opportunities and challenges associated with using ChatGPT and other LLMs for transforming biomedicine and health. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) have substantially pushed artificial intelligence (AI) research and applications in the last few years. They are currently able to achieve high effectiveness in different natural language processing (NLP) tasks, such as machine translation, named entity recognition, text classification, question answering, or text summarization. Recently, significant attention has been drawn to OpenAI's GPT models' capabilities and extremely accessible interface. LLMs are nowadays routinely used and studied for downstream tasks and specific applications with great success, pushing forward the state of the art in almost all of them. However, they also exhibit impressive inference capabilities when used off the shelf without further training. In this paper, we aim to study the behavior of pre‐trained language models (PLMs) in some inference tasks they were not initially trained for. Therefore, we focus our attention on very recent research works related to the inference capabilities of PLMs in some selected tasks such as factual probing and common‐sense reasoning. We highlight relevant achievements made by these models, as well as some of their current limitations that open opportunities for further research. This article is categorized under:Fundamental Concepts of Data and Knowledge > Key Design Issues in Data MiningTechnologies > Artificial Intelligence [ABSTRACT FROM AUTHOR]

Representation transfer is a widely used technique in natural language processing. We propose methods of cleaning the dominant dataset of text simplification (TS) WikiLarge in multi-views to remove errors that impact model training and fine-tuning. The results show that our method can effectively refine the dataset. We propose to take the pre-trained text representations from a similar task (e.g., text summarization) to text simplification to conduct a continue-fine-tuning strategy to improve the performance of pre-trained models on TS. This approach will speed up the training and make the model convergence easier. Besides, we also propose a new decoding strategy for simple text generation. It is able to generate simpler and more comprehensible text with controllable lexical simplicity. The experimental results show that our method can achieve good performance on many evaluation metrics. • Using sentence representations to refine the dataset. • Fine-tuning by taking text representations from similar tasks. • A new decoding strategy for simple text generation. [ABSTRACT FROM AUTHOR]

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG. [ABSTRACT FROM AUTHOR]

Today, most newspapers utilize social media to disseminate news. On the one hand, this results in an overload of related articles for social media users. On the other hand, since social media tends to form echo chambers around their users, different opinions and information may be hidden. Enabling users to access different information (possibly outside of their echo chambers, without the burden of reading entire articles, often containing redundant information) may be a step forward in allowing them to form their own opinions. To address this challenge, we propose a system that integrates Transformer neural models and text summarization models along with decision rules. Given a reference article already read by the user, our system first collects articles related to the same topic from a configurable number of different sources. Then, it identifies and summarizes the information that differs from the reference article and outputs the summary to the user. The core of the system is the sentence classification algorithm, which classifies sentences in the collected articles into three classes based on similarity with the reference article: sentences classified as dissimilar are summarized by using a pre-trained abstractive summarization model. We evaluated the proposed system in two steps. First, we assessed its effectiveness in identifying content differences between the reference article and the related articles by using human judgments obtained through crowdsourcing as ground truth. We obtained an average F1 score of 0.772 against average F1 scores of 0.797 and 0.676 achieved by two state-of-the-art approaches based, respectively, on model tuning and prompt tuning, which require an appropriate tuning phase and, therefore, greater computational effort. Second, we asked a sample of people to evaluate how well the summary generated by the system represents the information that is not present in the article read by the user. The results are extremely encouraging. Finally, we present a use case. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study of ChatGPT, a state-of-the-art language model that is revolutionizing generative text. We provide a comprehensive analysis of its architecture, training data, and evaluation metrics and explore its advancements and enhancements over time. Additionally, we examine the capabilities and limitations of ChatGPT in natural language processing (NLP) tasks, including language translation, text summarization, and dialogue generation. Furthermore, we compare ChatGPT to other language generation models and discuss its applicability in various tasks. Our study also addresses the ethical and privacy considerations associated with ChatGPT and provides insights into mitigation strategies. Moreover, we investigate the role of ChatGPT in cyberattacks, highlighting potential security risks. Lastly, we showcase the diverse applications of ChatGPT in different industries and evaluate its performance across languages and domains. This paper offers a comprehensive exploration of ChatGPT's impact on the NLP field. [ABSTRACT FROM AUTHOR]

In this paper, we present a rigorous mathematical examination of generative pre-trained transformer (GPT) models and their autoregressive self-supervised learning mechanisms. We begin by defining natural language space and knowledge space, which are two key concepts for understanding the dimensionality reduction process in GPT-based large language models (LLMs). By exploring projection functions and their inverses, we establish a framework for analyzing the language generation capabilities of these models. We then investigate the GPT representation space, examining its implications for the models' approximation properties. Finally, we discuss the limitations and challenges of GPT models and their learning mechanisms, considering trade-offs between complexity and generalization, as well as the implications of incomplete inverse projection functions. Our findings demonstrate that GPT models possess the capability to encode knowledge into low-dimensional vectors through their autoregressive self-supervised learning mechanism. This comprehensive analysis provides a solid mathematical foundation for future advancements in GPT-based LLMs, promising advancements in natural language processing tasks such as language translation, text summarization, and question answering due to improved understanding and optimization of model training and performance. [ABSTRACT FROM AUTHOR]

The tremendous increase in documents available on the Web has turned finding the relevant pieces of information into a challenging, tedious, and time-consuming activity. Text summarization is an important natural language processing (NLP) task used to reduce the reading requirements of text. Automatic text summarization is an NLP task that consists of creating a shorter version of a text document which is coherent and maintains the most relevant information of the original text. In recent years, automatic text summarization has received significant attention, as it can be applied to a wide range of applications such as the extraction of highlights from scientific papers or the generation of summaries of news articles. In this research project, we are focused mainly on abstractive text summarization that extracts the most important contents from a text in a rephrased form. The main purpose of this project is to summarize texts in German. Unfortunately, most pretrained models are only available for English. We therefore focused on the German BERT multilingual model and the BART monolingual model for English, with a consideration of translation possibilities. As the source of the experiment setup, took the German Wikipedia article dataset and compared how well the multilingual model performed for German text summarization when compared to using machine-translated text summaries from monolingual English language models. We used the ROUGE-1 metric to analyze the quality of the text summarization. [ABSTRACT FROM AUTHOR]

Considering the ever-growing volume of electronic documents made available in our daily lives, the need for an efficient tool to capture their gist increases as well. Automatic text summarization, which is a process of shortening long text and extracting valuable information, has been of great interest for decades. Due to the difficulties of semantic understanding and the requirement of large training data, the development of this research field is still challenging and worth investigating. In this paper, we propose an automated text summarization approach with the adaptation of static and contextual representations based on an extractive approach to address the research gaps. To better obtain the semantic expression of the given text, we explore the combination of static embeddings from GloVe (Global Vectors) and the contextual embeddings from BERT (Bidirectional Encoder Representations from Transformer) and GPT (Generative Pre-trained Transformer) based models. In order to reduce human annotation costs, we employ policy gradient reinforcement learning to perform unsupervised training. We conduct empirical studies on the public dataset, Gigaword. The experimental results show that our approach achieves promising performance and is competitive with various state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Eliciting informative user opinions from online reviews is a key success factor for innovative product design and development. The unstructured, noisy, and verbose nature of user reviews, however, often complicate large-scale need finding in a format useful for designers without losing important information. Recent advances in abstractive text summarization have created the opportunity to systematically generate opinion summaries from online reviews to inform the early stages of product design and development. However, two knowledge gaps hinder the applicability of opinion summarization methods in practice. First, there is a lack of formal mechanisms to guide the generative process with respect to different categories of product attributes and user sentiments. Second, the annotated training datasets needed for supervised training of abstractive summarization models are often difficult and costly to create. This article addresses these gaps by (1) devising an efficient computational framework for abstractive opinion summarization guided by specific product attributes and sentiment polarities, and (2) automatically generating a synthetic training dataset that captures various degrees of granularity and polarity. A hierarchical multi-instance attribute-sentiment inference model is developed for assembling a high-quality synthetic dataset, which is utilized to fine-tune a pretrained language model for abstractive summary generation. Numerical experiments conducted on a large dataset scraped from three major e-Commerce retail stores for apparel and footwear products indicate the performance, feasibility, and potentials of the developed framework. Several directions are provided for future exploration in the area of automated opinion summarization for user-centered design. [ABSTRACT FROM AUTHOR]

Long document summarization poses obstacles to current generative transformer-based models because of the broad context to process and understand. Indeed, detecting long-range dependencies is still challenging for today's state-of-the-art solutions, usually requiring model expansion at the cost of an unsustainable demand for computing and memory capacities. This paper introduces Emma, a novel efficient memory-enhanced transformer-based architecture. By segmenting a lengthy input into multiple text fragments, our model stores and compares the current chunk with previous ones, gaining the capability to read and comprehend the entire context over the whole document with a fixed amount of GPU memory. This method enables the model to deal with theoretically infinitely long documents, using less than 18 and 13 GB of memory for training and inference, respectively. We conducted extensive performance analyses and demonstrate that Emma achieved competitive results on two datasets of different domains while consuming significantly less GPU memory than competitors do, even in low-resource settings. [ABSTRACT FROM AUTHOR]

The increasing amount of legal information available online is overwhelming for both citizens and legal professionals, making it difficult and time-consuming to find relevant information and keep up with the latest legal developments. Automatic text summarization techniques can be highly beneficial as they save time, reduce costs, and lessen the cognitive load of legal professionals. However, applying these techniques to legal documents poses several challenges due to the complexity of legal documents and the lack of needed resources, especially in linguistically under-resourced languages, such as the Greek language. In this paper, we address automatic summarization of Greek legal documents. A major challenge in this area is the lack of suitable datasets in the Greek language. In response, we developed a new metadata-rich dataset consisting of selected judgments from the Supreme Civil and Criminal Court of Greece, alongside their reference summaries and category tags, tailored for the purpose of automated legal document summarization. We also adopted several state-of-the-art methods for abstractive and extractive summarization and conducted a comprehensive evaluation of the methods using both human and automatic metrics. Our results: (i) revealed that, while extractive methods exhibit average performance, abstractive methods generate moderately fluent and coherent text, but they tend to receive low scores in relevance and consistency metrics; (ii) indicated the need for metrics that capture better a legal document summary's coherence, relevance, and consistency; (iii) demonstrated that fine-tuning BERT models on a specific upstream task can significantly improve the model's performance. [ABSTRACT FROM AUTHOR]

The extractive summarization approach involves selecting the source document's salient sentences to build a summary. One of the most important aspects of extractive summarization is learning and modelling cross-sentence associations. Inspired by the popularity of Transformer-based Bidirectional Encoder Representations (BERT) pretrained linguistic model and graph attention network (GAT) having a sophisticated network that captures intersentence associations, this research work proposes a novel neural model N-GPETS by combining heterogeneous graph attention network with BERT model along with statistical approach using TF-IDF values for extractive summarization task. Apart from sentence nodes, N-GPETS also works with different semantic word nodes of varying granularity levels that serve as a link between sentences, improving intersentence interaction. Furthermore, proposed N-GPETS becomes more improved and feature-rich by integrating graph layer with BERT encoder at graph initialization step rather than employing other neural network encoders such as CNN or LSTM. To the best of our knowledge, this work is the first attempt to combine the BERT encoder and TF-IDF values of the entire document with a heterogeneous attention graph structure for the extractive summarization task. The empirical outcomes on benchmark news data sets CNN/DM show that the proposed model N-GPETS gets favorable results in comparison with other heterogeneous graph structures employing the BERT model and graph structures without the BERT model. [ABSTRACT FROM AUTHOR]

The enormous quantity of text makes it challenging for users to obtain the key information and knowledge. Automatic text summarization can alleviate this problem by providing reliable summaries for massive text documents. During the last decade, significant achievements have been made in text summarization. We conduct this survey to explore what research community is focused on, the application scenarios of summarization, the state-of-the-art techniques and methods, and to analyze the challenges and future direction. We summarize that incorporating with natural language processing, previous text summarization research applied knowledge-based methods, graph-based methods, statistical learning methods, and deep learning methods. Applying large language model to text summarization is still in its early stages. By analyzing current research progress, we conclude that understand semantic information and specific domain knowledge is required for text summarization, and the conciseness and readability of the summary should be ensured. The future research opportunity is automatic knowledge summarization, and more research effort is urgently needed to explore. • Significant achievements of automatic text summarization have been made. • We aim to explore the research community of automatic text summarization. • Incorporating with NLP, text summarization applied knowledge-based, graph-based and machine learning methods. • The combination of extractive and abstractive strategies is required, which can ensure the quality of the summary. • The future research opportunity is automatic knowledge summarization. [ABSTRACT FROM AUTHOR]

Specifically focusing on the landscape of abstractive text summarization, as opposed to extractive techniques, this survey presents a comprehensive overview, delving into state-of-the-art techniques, prevailing challenges, and prospective research directions. We categorize the techniques into traditional sequence-to-sequence models, pre-trained large language models, reinforcement learning, hierarchical methods, and multi-modal summarization. Unlike prior works that did not examine complexities, scalability and comparisons of techniques in detail, this review takes a comprehensive approach encompassing state-of-the-art methods, challenges, solutions, comparisons, limitations and charts out future improvements — providing researchers an extensive overview to advance abstractive summarization research. We provide vital comparison tables across techniques categorized — offering insights into model complexity, scalability and appropriate applications. The paper highlights challenges such as inadequate meaning representation, factual consistency, controllable text summarization, cross-lingual summarization, and evaluation metrics, among others. Solutions leveraging knowledge incorporation and other innovative strategies are proposed to address these challenges. The paper concludes by highlighting emerging research areas like factual inconsistency, domain-specific, cross-lingual, multilingual, and long-document summarization, as well as handling noisy data. Our objective is to provide researchers and practitioners with a structured overview of the domain, enabling them to better understand the current landscape and identify potential areas for further research and improvement. [Display omitted] • Overview of state-of-the-art techniques in abstractive text summarization. • Comparative analysis of models in abstractive summarization. • Identification of challenges and potential improvements in the field. • Exploration of future research directions and emerging frontiers. • Holistic survey of abstractive text summarization. [ABSTRACT FROM AUTHOR]

A novel methodology is introduced for extracting entities from noisy scanned documents by using end-to-end data and reformulating the entity extraction task as a text summarization problem. This approach offers two significant advantages over traditional entity extraction methods while maintaining comparable performance. First, it utilizes preexisting data to construct datasets, thereby eliminating the need for labor-intensive annotation procedures. Second, it employs multitask learning, enabling the training of a model via a single dataset. To evaluate our approach against state-of-the-art methods, we adapted three commonly used datasets, namely, Conference on Natural Language Learning (CoNLL++), few-shot named entity recognition (Few-NERD), and WikiNEuRal domain adaptation (WikiNEuRal + DA), to the format required by our methodology. We subsequently fine-tuned four sequence-to-sequence models: text-to-text transfer transformer (T5), fine-tuned language net T5 (FLAN-T5), bidirectional autoregressive transformer (BART), and pretraining with extracted gap sentences for abstractive summarization sequence-to-sequence models (PEGASUS). The results indicate that, in the absence of optical character recognition (OCR) noise, the BART model performs comparably to state-of-the-art methods. Furthermore, the performance degradation was limited to 3.49–5.23% when 39–62% of the sentences contained OCR noise. This performance is significantly superior to that of previous studies, which reported a 10–20% decrease in the F1 score with texts that had a 20% OCR error rate. Our experimental results demonstrate that a single model trained via our methodology can reliably extract entities from noisy OCRed texts, unlike existing state-of-the-art approaches, which require separate models for correcting OCR errors and extracting entities. [ABSTRACT FROM AUTHOR]

• Text summarization in scientific research is crucial but time consuming and labor intensive, and it requires specific expertise; here, NLP is playing a role. • ChatGPT's drug information summarization was evaluated against human experts using >14 000 records from the FDA Labeling document for the first time. • ChatGPT reliably generates summaries closely resembling those of human experts, particularly in the context of summarizing drug safety information from labeling documents. • ChatGPT and its derivatives are valuable in drug discovery, improving drug labeling access and supporting FDA review processes. Text summarization is crucial in scientific research, drug discovery and development, regulatory review, and more. This task demands domain expertise, language proficiency, semantic prowess, and conceptual skill. The recent advent of large language models (LLMs), such as ChatGPT, offers unprecedented opportunities to automate this process. We compared ChatGPT-generated summaries with those produced by human experts using FDA drug labeling documents. The labeling contains summaries of key labeling sections, making them an ideal human benchmark to evaluate ChatGPT's summarization capabilities. Analyzing >14 000 summaries, we observed that ChatGPT-generated summaries closely resembled those generated by human experts. Importantly, ChatGPT exhibited even greater similarity when summarizing drug safety information. These findings highlight ChatGPT's potential to accelerate work in critical areas, including drug safety. [ABSTRACT FROM AUTHOR]

With the advent of transformer-based architectures, the contextual representation of text data has leveraged the query and the document to be represented in low-dimensional dense vector space. These vectors are learned embeddings of fixed sizes, resulting in deeper text understanding. In this study, we designed a pipeline for effectively retrieving documents from a large search space by combining the deeper text understanding capabilities of the transformer-based BERT model and a phrase embedding-based query expansion model. To learn the contextual representations, we fine-tuned a deep semantic matching model by separately encoding the document and the query. The encoder model is based on the Sentence BERT (SBERT) architecture, which separately generates dense vector representations of documents and queries. The study has also addressed the maximum token length limitation of transformer-based models through the summarization of lengthy documents. In addition, to improve the clarity and completeness of short queries and reduce the semantic gap, a phrase embedding-based query expansion model is employed. The documents and their dense vectors are indexed using the Elasticsearch engine, and matched them with query vectors for retrieving query-specific documents. Finally, the BERT-based cross-encoder model is used to re-rank the relevant records for each query. It performs full self-attention over the inputs, and yields richer text interactions to produce the final results. To assess performance, experiments are conducted on two well-known datasets, TREC-CDS-2014 and OHSUMED. A comparative analysis is carried out, which clearly demonstrates that the proposed framework produced competitive retrieval results. • Transformer-based contextual text representation approach is proposed for IR. • Bi-Encoder architecture is applied to learn the representations of documents & query. • BERT-based summarization is applied to address the limitation on sequence length. • Phrase Embedding-based QE technique is employed to expand short and unclear queries. • Re-ranking of the retrieval results is performed using the cross encoder model. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Abstractive dialogue summarization requires distilling and rephrasing key information from noisy multi-speaker documents. Combining pre-trained language models with input augmentation techniques has recently led to significant research progress. However, existing solutions still struggle to select relevant chat segments, primarily relying on open-domain and unsupervised annotators not tailored to the actual needs of the summarization task. In this paper, we propose DearWatson , a task-aware utterance-level annotation framework for improving the effectiveness and interpretability of pre-trained dialogue summarization models. Precisely, we learn relevant utterances in the source document and mark them with special tags, that then act as supporting evidence for the generated summary. Quantitative experiments are conducted on two datasets made up of real-life messenger conversations. The results show that DearWatson allows model attention to focus on salient tokens, achieving new state-of-the-art results in three evaluation metrics, including semantic and factuality measures. Human evaluation proves the superiority of our solution in semantic consistency and recall. Finally, extensive ablation studies confirm each module's importance, also exploring different annotation strategies and parameter-efficient fine-tuning of large generative language models. [ABSTRACT FROM AUTHOR]

With the development of pre-trained language models and large-scale datasets, automatic text summarization has attracted much attention from the community of natural language processing, but the progress of automatic summarization evaluation has stagnated. Although there have been efforts to improve automatic summarization evaluation, ROUGE has remained one of the most popular metrics for nearly 20 years due to its competitive evaluation performance. However, ROUGE is not perfect, there are studies have shown that it is suffering from inaccurate evaluation of abstractive summarization and limited diversity of generated summaries, both caused by lexical bias. To avoid the bias of lexical similarity, more and more meaningful embedding-based metrics have been proposed to evaluate summaries by measuring semantic similarity. Due to the challenge of accurately measuring semantic similarity, none of them can fully replace ROUGE as the default automatic evaluation toolkit for text summarization. To address the aforementioned problems, we propose a compromise evaluation framework (ROUGE-SEM) for improving ROUGE with semantic information, which compensates for the lack of semantic awareness through a semantic similarity module. According to the differences in semantic similarity and lexical similarity, summaries are classified into four categories for the first time, including good-summary, pearl-summary, glass-summary, and bad-summary. In particular, the back-translation technique is adopted to rewrite pearl-summary and glass-summary that are inaccurately evaluated by ROUGE to alleviate lexical bias. Through this pipeline framework, summaries are first classified by candidate summary classifier, then rewritten by categorized summary rewriter, and finally scored by rewritten summary scorer, which are efficiently evaluated in a manner consistent with human behavior. When measured using Pearson, Spearman, and Kendall rank coefficients, our proposal achieves comparable or higher correlations with human judgments than several state-of-the-art automatic summarization evaluation metrics in dimensions of coherence, consistency, fluency, and relevance. This also suggests that improving ROUGE with semantics is a promising direction for automatic summarization evaluation. [ABSTRACT FROM AUTHOR]

Although pretrained language models achieve high performance on various natural language processing tasks, they still require further improvements in the sentence embedding task. Many studies have improved performance in this task using pre-trained language models and contrastive learning, but these approaches are limited because they are based on naive average pooling and CLS tokens. Therefore, we propose an advanced sentence-embedding method based on weighted pooling that considers token importance. Specifically, the token importance is calculated by combining an explainable artificial-intelligence module with a text summarization model, and the final sentence embedding is derived through weighted pooling token embedding and token importance. Thus, we derive a sentence embedding that considers both the local information of the token embedding and the global information of the entire sentence. Experimental results reveal that our proposed sentence embedding outperforms other models on both text similarity tasks and text classification. Moreover, the proposed method's robustness is verified through the results of an ablation study. [ABSTRACT FROM AUTHOR]

Recently, large language models have shown great success on various abstractive summarization datasets. These datasets consist of numerous data that are enough to train a large number of parameters. However, for a new domain, there is a lack of labeled data to train those parameters and the model is easily overfitted to a small amount of data. In addition, because annotating document-summary pairs is too expensive and transfer learning using high-resource datasets causes a domain shifting problem, a low-resource abstractive summarization task is becoming necessary. Herein, we propose an efficient framework for low-resource abstractive summarization using a pointer-generator network and a meta-learning technique to address the above problems. Meta-learning using existing high-resource datasets enables our model to rapidly adapt to a new domain using limited data to solve the domain shifting problem. In addition, we explore the copy mechanism using a pointer-generator network that can copy words from a source document when generating a summary. The experimental results on 11 different datasets show that the proposed model outperforms the previous state-of-the-art models in low-resource abstractive summarization on most of the datasets. [ABSTRACT FROM AUTHOR]