Search

Nowadays, due to the constantly growing amount of textual information, automatic text summarization constitutes an important research area in natural language processing. In this work, we present a novel framework that combines semantic graph representations along with deep learning predictions to generate abstractive summaries of single documents, in an effort to utilize a semantic representation of the unstructured textual content in a machine-readable, structured, and concise manner. The overall framework is based on a well defined methodology for performing semantic graph parsing, graph construction, graph transformations for machine learning models and deep learning predictions. The employed semantic graph representation focuses on using the model of abstract meaning representation. Several combinations of graph construction and graph transformation methods are investigated to specify the most efficient of them for the machine learning models. Additionally, a range of deep learning architectures is examined, including a sequence-to-sequence attentive network, reinforcement learning, transformer-based architectures, and pre-trained neural language models. In this direction, a semantic graph representation of an original text is extracted, and then the present framework formulates the problem as a graph-to-summary learning problem to predict a summary of an original text. To the best of our knowledge, this formulation of graph-to-summary predictions in abstractive text summarization, without other intermediate steps in the machine learning phase, has not been presented in the relevant literature. Another important contribution is an introduction of a measure for assessing the factual consistency of the generated summaries in an effort to provide a qualitative evaluation. To assess the framework, an extensive experimental procedure is presented that uses popular datasets to evaluate key aspects of the proposed approach. The obtained results exhibit promising performance, validating the robustness of the proposed framework. [ABSTRACT FROM AUTHOR]

Medical imaging description and disease diagnosis are vitally important yet time-consuming. Automated diagnosis report generation (DRG) from medical imaging description can reduce clinicians' workload and improve their routine efficiency. To address this natural language generation task, fine-tuning a pre-trained large language model (LLM) is cost-effective and indispensable, and its success has been witnessed in many downstream applications. However, semantic inconsistency of sentence embeddings has been massively observed from undesirable repetitions or unnaturalness in text generation. To address the underlying issue of anisotropic distribution of token representation, in this study, a contrastive learning penalized cross-entropy (CLpCE) objective function is implemented to enhance the semantic consistency and accuracy of token representation by guiding the fine-tuning procedure towards a specific task. Furthermore, to improve the diversity of token generation in text summarization and to prevent sampling from unreliable tail of token distributions, a diversity contrastive search (DCS) decoding method is designed for restricting the report generation derived from a probable candidate set with maintained semantic coherence. Furthermore, a novel metric named the maximum of token repetition ratio (maxTRR) is proposed to estimate the token diversity and to help determine the candidate output. Based on the LLM of a generative pre-trained Transformer 2 (GPT-2) of Chinese version, the proposed CLpCE with DCS (CLpCEwDCS) decoding framework is validated on 30,000 desensitized text samples from the "Medical Imaging Diagnosis Report Generation" track of 2023 Global Artificial Intelligence Technology Innovation Competition. Using four kinds of metrics evaluated from n-gram word matching, semantic relevance, and content similarity as well as the maxTRR metric extensive experiments reveal that the proposed framework effectively maintains semantic coherence and accuracy (BLEU-1, 0.4937; BLEU-2, 0.4107; BLEU-3, 0.3461; BLEU-4, 0.2933; METEOR, 0.2612; ROUGE, 0.5182; CIDER, 1.4339) and improves text generation diversity and naturalness (maxTRR, 0.12). The phenomenon of dull or repetitive text generation is common when fine-tuning pre-trained LLMs for natural language processing applications. This study might shed some light on relieving this issue by developing comprehensive strategies to enhance semantic coherence, accuracy and diversity of sentence embeddings. [ABSTRACT FROM AUTHOR]

This scientific research study focuses on the advancements in Natural Language Processing (NLP) driven by large-scale parallel corpora and presents a comprehensive methodology for creating a parallel, multilingual corpus using NLP techniques and semantic technologies, with a particular focus on washing machine manuals. The study highlights the significant progress made in NLP through the utilization of large-scale parallel corpora and advanced NLP techniques. The successful creation of a parallel, multilingual corpus for washing machine manuals, coupled with the integration of semantic technologies and ontology modeling, demonstrates the broad applicability and potential of NLP in diverse domains.The research covers various aspects, including text extraction, segmentation, and the development of specialized pipelines for question-answering, translation, and text summarization tailored for washing machine manuals. Translation experiments using fine-tuned models demonstrated the feasibility of providing washing machine manuals in local languages, expanding accessibility and understanding for users worldwide. Additionally, the study explored text summarization using a powerful transformer-based model, which exhibited remarkable proficiency in generating concise and coherent summaries from complex input texts. The implementation of a question-answering pipeline showcased the effectiveness of various language models in handling question-answering tasks with high accuracy and effectiveness.Additionally, the article discusses the processes of data collection, information preparation, ontology creation, alignment strategies, and text analytics. Furthermore, the study addresses the challenges and potential future developments in this field, offering insights into the promising applications of NLP in the context of washing machine manuals. [ABSTRACT FROM AUTHOR]

Data augmentation entails artificially expanding the dataset's size by applying various transformations to the existing raw data. Enhancing the quality and quantity of the datasets with varying sizes by employing varieddata augmentation techniques has immense importance in the field on Natural Language Processing. Several notable applications for instance text classification, sentiment analysis, text summarization, etc. have proven to be benefitted immensely with the employment of text augmentation techniques. Hence, the paper focuses on efficient text classification using varied datasets of different sizes; small- 500 instances, medium-5564 instances and large-43934 instances.The work considers the standard DistilBERT model, a popular transformer-based language model and presents the impact on the performance of the modelafter employing different text augmentation techniques. The study specifically focuses on three augmentation methods: (a) Synonym augmentation:that involves replacing words with their synonyms to enhance vocabulary diversity and generalization, (b) Contextual word embeddings that enriches semantic understanding by leveraging pre-trained language models, and (c) Black translation that entails translating the text into a another different language and then translating it back, introducing variations in the data and capturing different linguistic patterns.Additionally,the work also discusses the combined effect of employing all three augmentation techniques simultaneously. Moreover, the study also aims compares the relation between the dataset sizes and the performance of the augmentation techniques. The study considers three standard datasets for the analysis and presents a comprehensive analysis using accuracy and F1 score as evaluation metrics. The results highlight the efficacy of each technique across small, medium, and large datasets, enabling a nuanced understanding of their benefits in different data scenarios. The findings indicate the varying degrees of improvement achieved through each augmentation technique.The enhancement achieved by applying text augmentation varied from around 2% on large datasets to 20% on smaller datasets. [ABSTRACT FROM AUTHOR]

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) and have been widely adopted in various applications such as ma)chine translation, chatbots, text summarization, and so on. However, the use of LLMs has raised concerns about their potential safety and security risks. In this survey, we explore the safety implications of LLMs, including ethical considerations, hallucination, and prompt injection. We also discuss current research efforts to mitigate these risks and identify areas for future research. Our survey provides a comprehen)sive overview of the safety concerns related to LLMs, which can help researchers and practitioners in the NLP community develop more safe and ethical appli)cations of LLMs. [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]

The transformer model is a famous natural language processing model proposed by Google in 2017. Now, with the extensive development of deep learning, many natural language processing tasks can be solved by deep learning methods. After the BERT model was proposed, many pre-trained models such as the XLNet model, the RoBERTa model, and the ALBERT model were also proposed in the research community. These models perform very well in various natural language processing tasks. In this paper, we describe and compare these well-known models. In addition, we also apply several types of existing and well-known models which are the BERT model, the XLNet model, the RoBERTa model, the GPT2 model, and the ALBERT model to different existing and well-known natural language processing tasks, and analyze each model based on their performance. There are a few papers that comprehensively compare various transformer models. In our paper, we use six types of well-known tasks, such as sentiment analysis, question answering, text generation, text summarization, name entity recognition, and topic modeling tasks to compare the performance of various transformer models. In addition, using the existing models, we also propose ensemble learning models for the different natural language processing tasks. The results show that our ensemble learning models perform better than a single classifier on specific tasks. [ABSTRACT FROM AUTHOR]

This document is a summary of a special issue of the journal Future Internet, focusing on the state of Future Internet Technology in Italy. The issue covers a range of topics, including anonymous service delivery, virtual environments for furnishings sales, Italian-language sequence-to-sequence models for text summarization, knowledge scaffolding in Wikipedia, the integration of Operation Technology and Information Technology networking in Industry 4.0, a digital platform for healthcare operators, self-admitted technical debt in blockchain initiatives, unified analytics for smart cities, the integration of natural language processing and artificial intelligence in e-learning, and a system for attack detection in network architectures. The authors provide detailed explanations and evaluations of each topic, highlighting their potential benefits and applications. [Extracted from the article]

(1) Background: Information overload challenges decision-making in the Industry 4.0 era. While Natural Language Processing (NLP), especially Automatic Text Summarization (ATS), offers solutions, issues with factual accuracy persist. This research bridges cognitive neuroscience and NLP, aiming to improve model interpretability. (2) Methods: This research examined four fact extraction techniques: dependency relation, named entity recognition, part-of-speech tagging, and TF-IDF, in order to explore their correlation with human EEG signals. Representational Similarity Analysis (RSA) was applied to gauge the relationship between language models and brain activity. (3) Results: Named entity recognition showed the highest sensitivity to EEG signals, marking the most significant differentiation between factual and non-factual words with a score of −0.99. The dependency relation followed with −0.90, while part-of-speech tagging and TF-IDF resulted in 0.07 and −0.52, respectively. Deep language models such as GloVe, BERT, and GPT-2 exhibited noticeable influences on RSA scores, highlighting the nuanced interplay between brain activity and these models. (4) Conclusions: Our findings emphasize the crucial role of named entity recognition and dependency relations in fact extraction and demonstrate the independent effects of different models and TOIs on RSA scores. These insights aim to refine algorithms to reflect human text processing better, thereby enhancing ATS models' factual integrity. [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]

Copyright of Journal of Engineering & Architectural Faculty of Eskisehir Osmangazi University / Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi is the property of Eskisehir Osmangazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• 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]

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]