Real-world Text Research Articles

USING AUTHENTIC MATERIALS TO DEVELOP STUDENTS’ CRITICAL READING ABILITY

This article uncovers the potential of authentic materials, such as real-world texts, materials and resources, in developing students' critical reading abilities. It argues that traditional textbook-based approaches often fail to engage students in meaningful ways and lack the complexity and relevance required for fostering critical thinking skills. The article examines specificstrategies for incorporating authentic materials into the classroom, highlighting their effectiveness in motivating students, promoting deeper understanding of content, and developing essential critical reading skills such as analysis, evaluation, and synthesis. The benefits of using authentic materials for various subject areas and age groups are discussed, alongside practical tips and resources for educators.

Novel embeddings improve the prediction of risk perception

We assess whether the classic psychometric paradigm of risk perception can be improved or supplanted by novel approaches relying on language embeddings. To this end, we introduce the Basel Risk Norms, a large data set covering 1004 distinct sources of risk (e.g., vaccination, nuclear energy, artificial intelligence) and compare the psychometric paradigm against novel text and free-association embeddings in predicting risk perception. We find that an ensemble model combining text and free association rivals the predictive accuracy of the psychometric paradigm, captures additional affect and frequency-related dimensions of risk perception not accounted for by the classic approach, and has greater range of applicability to real-world text data, such as news headlines. Overall, our results establish the ensemble of text and free-association embeddings as a promising new tool for researchers and policymakers to track real-world risk perception.

From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts

Word Rain is a development of the classic word cloud. It addresses some of the limitations of word clouds, in particular the lack of a semantically motivated positioning of the words, and the use of font size as a sole indicator of word prominence. Word Rain uses the semantic information encoded in a distributional semantics-based language model – reduced into one dimension – to position the words along the x-axis. Thereby, the horizontal positioning of the words reflects semantic similarity. Font size is still used to signal word prominence, but this signal is supplemented with a bar chart, as well as with the position of the words on the y-axis. We exemplify the use of Word Rain by three concrete visualization tasks, applied on different real-world texts and document collections on climate change. In these case studies, word2vec models, reduced to one dimension with t-SNE, are used to encode semantic similarity, and TF-IDF is used for measuring word prominence. We evaluate the technique further by carrying out domain expert reviews.

Text Image Inpainting via Global Structure-Guided Diffusion Models

Real-world text can be damaged by corrosion issues caused by environmental or human factors, which hinder the preservation of the complete styles of texts, e.g., texture and structure. These corrosion issues, such as graffiti signs and incomplete signatures, bring difficulties in understanding the texts, thereby posing significant challenges to downstream applications, e.g., scene text recognition and signature identification. Notably, current inpainting techniques often fail to adequately address this problem and have difficulties restoring accurate text images along with reasonable and consistent styles. Formulating this as an open problem of text image inpainting, this paper aims to build a benchmark to facilitate its study. In doing so, we establish two specific text inpainting datasets which contain scene text images and handwritten text images, respectively. Each of them includes images revamped by real-life and synthetic datasets, featuring pairs of original images, corrupted images, and other assistant information. On top of the datasets, we further develop a novel neural framework, Global Structure-guided Diffusion Model (GSDM), as a potential solution. Leveraging the global structure of the text as a prior, the proposed GSDM develops an efficient diffusion model to recover clean texts. The efficacy of our approach is demonstrated by thorough empirical study, including a substantial boost in both recognition accuracy and image quality. These findings not only highlight the effectiveness of our method but also underscore its potential to enhance the broader field of text image understanding and processing. Code and datasets are available at: https://github.com/blackprotoss/GSDM.

Evaluating sentiment analysis and word embedding techniques on Brexit

<p>In this study, we investigate the effectiveness of pre-trained word embeddings for sentiment analysis on a real-world topic, namely Brexit. We compare the performance of several popular word embedding models such global vectors for word representation (GloVe), FastText, word to vec (word2vec), and embeddings from language models (ELMo) on a dataset of tweets related to Brexit and evaluate their ability to classify the sentiment of the tweets as positive, negative, or neutral. We find that pre-trained word embeddings provide useful features for sentiment analysis and can significantly improve the performance of machine learning models. We also discuss the challenges and limitations of applying these models to complex, real-world texts such as those related to Brexit.</p><p> </p>

Siamese capsule network with position correlation and integrating articles of law for Chinese similar case matching

The purpose of the Chinese similar case matching task is to compare the similarity of two case texts with a given anchor text and find out which text is more similar to the anchor text. In the area of law, it plays an important role and has been of interest to many researchers. Previous approaches have compared legal texts only at the text semantic level, without incorporating article information of law. In addition, the position correlation of words in case texts is often important, but it has not been considered in previous approaches. This paper proposes a method which extracts features from the semantic similarity level and from the level of related articles of law, respectively, to enable similarity comparisons of legal case texts. When similarity comparisons are made at the semantic similarity level, a novel capsule network method is proposed based on siamese structure that introduces the position correlation and the routing mechanism within the capsule network is improved so that deep text features between case pairs can be learned. When similarity comparisons are made at the level of related articles of law, related articles of law are selected and coded and interacted with the case text features to generate legal features. Experiment is conducted with a real-world legal text dataset, and the proposed model outperformed all baseline models, demonstrating effectiveness of the proposed model. Further, to confirm the generality of the improved capsule network proposed in the paper on long text datasets, this paper also carried out experiments on two long text datasets, demonstrating effectiveness of the improved capsule network proposed in the model.

A Novel Neural Ensemble Architecture for On-the-fly Classification of Evolving Text Streams

We study on-the-fly classification of evolving text streams in which the relation between the input data and target labels changes over time—i.e., “concept drift.” These variations decrease the model’s performance, as predictions become less accurate over time and they necessitate a more adaptable system. While most studies focus on concept drift detection and handling with ensemble approaches, the application of neural models in this area is relatively less studied. We introduce Adaptive Neural Ensemble Network ( AdaNEN ), a novel ensemble-based neural approach, capable of handling concept drift in data streams. With our novel architecture, we address some of the problems neural models face when exploited for online adaptive learning environments. Most current studies address concept drift detection and handling in numerical streams, and the evolving text stream classification remains relatively unexplored. We hypothesize that the lack of public and large-scale experimental data could be one reason. To this end, we propose a method based on an existing approach for generating evolving text streams by introducing various types of concept drifts to real-world text datasets. We provide an extensive evaluation of our proposed approach using 12 state-of-the-art baselines and 13 datasets. We first evaluate concept drift handling capability of AdaNEN and the baseline models on evolving numerical streams; this aims to demonstrate the concept drift handling capabilities of our method on a general spectrum and motivate its use in evolving text streams. The models are then evaluated in evolving text stream classification. Our experimental results show that AdaNEN consistently outperforms the existing approaches in terms of predictive performance with conservative efficiency.

Utility analysis and demonstration of real-world clinical texts: A case study on Japanese cancer-related EHRs.

Real-world data (RWD) in the medical field, such as electronic health records (EHRs) and medication orders, are receiving increasing attention from researchers and practitioners. While structured data have played a vital role thus far, unstructured data represented by text (e.g., discharge summaries) are not effectively utilized because of the difficulty in extracting medical information. We evaluated the information gained by supplementing structured data with clinical concepts extracted from unstructured text by leveraging natural language processing techniques. Using a machine learning-based pretrained named entity recognition tool, we extracted disease and medication names from real discharge summaries in a Japanese hospital and linked them to medical concepts using medical term dictionaries. By comparing the diseases and medications mentioned in the text with medical codes in tabular diagnosis records, we found that: (1) the text data contained richer information on patient symptoms than tabular diagnosis records, whereas the medication-order table stored more injection data than text. In addition, (2) extractable information regarding specific diseases showed surprisingly small intersections among text, diagnosis records, and medication orders. Text data can thus be a useful supplement for RWD mining, which is further demonstrated by (3) our practical application system for drug safety evaluation, which exhaustively visualizes suspicious adverse drug effects caused by the simultaneous use of anticancer drug pairs. We conclude that proper use of textual information extraction can lead to better outcomes in medical RWD mining.

A study of generative large language model for medical research and healthcare

There are enormous enthusiasm and concerns in applying large language models (LLMs) to healthcare. Yet current assumptions are based on general-purpose LLMs such as ChatGPT, which are not developed for medical use. This study develops a generative clinical LLM, GatorTronGPT, using 277 billion words of text including (1) 82 billion words of clinical text from 126 clinical departments and approximately 2 million patients at the University of Florida Health and (2) 195 billion words of diverse general English text. We train GatorTronGPT using a GPT-3 architecture with up to 20 billion parameters and evaluate its utility for biomedical natural language processing (NLP) and healthcare text generation. GatorTronGPT improves biomedical natural language processing. We apply GatorTronGPT to generate 20 billion words of synthetic text. Synthetic NLP models trained using synthetic text generated by GatorTronGPT outperform models trained using real-world clinical text. Physicians’ Turing test using 1 (worst) to 9 (best) scale shows that there are no significant differences in linguistic readability (p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that physicians cannot differentiate them (p < 0.001). This study provides insights into the opportunities and challenges of LLMs for medical research and healthcare.

A COPRAS-based Approach to Multi-Label Feature Selection for Text Classification

In this article, we present a novel approach for text classification feature selection using a pseudo-relation matrix constructed with ridge regression. This approach involves generating a matrix that captures the relationship between features and target variables and then using that matrix to create a multi-criteria decision making (MCDM) problem. We then utilize the Complex Proportional Assessment (COPRAS) method to rank features in order of importance. To assess the performance of our proposed algorithm, we conduct tests on ten real-world text datasets and compare our results to the existing methods. Our findings indicate that the proposed approach outperforms other methods, and we provide statistical significance to support our claims. Our proposed algorithm provides a viable answer for researchers looking for efficient and effective feature selection methods for text data analysis, which can lead to a better understanding and interpretation of the underlying text.

Accelerating Aggregation Queries on Unstructured Streams of Data

Analysts and scientists are interested in querying streams of video, audio, and text to extract quantitative insights. For example, an urban planner may wish to measure congestion by querying the live feed from a traffic camera. Prior work has used deep neural networks (DNNs) to answer such queries in the batch setting. However, much of this work is not suited for the streaming setting because it requires access to the entire dataset before a query can be submitted or is specific to video. Thus, to the best of our knowledge, no prior work addresses the problem of efficiently answering queries over multiple modalities of streams. In this work we propose InQuest, a system for accelerating aggregation queries on unstructured streams of data with statistical guarantees on query accuracy. InQuest leverages inexpensive approximation models ("proxies") and sampling techniques to limit the execution of an expensive high-precision model (an "oracle") to a subset of the stream. It then uses the oracle predictions to compute an approximate query answer in real-time. We theoretically analyzed InQuest and show that the expected error of its query estimates converges on stationary streams at a rate inversely proportional to the oracle budget. We evaluated our algorithm on six real-world video and text datasets and show that InQuest achieves the same root mean squared error (RMSE) as two streaming baselines with up to 5.0x fewer oracle invocations. We further show that InQuest can achieve up to 1.9x lower RMSE at a fixed number of oracle invocations than a state-of-the-art batch setting algorithm.

Joint learning of text alignment and abstractive summarization for long documents via unbalanced optimal transport

Abstract Recently, neural abstractive text summarization (NATS) models based on sequence-to-sequence architecture have drawn a lot of attention. Real-world texts that need to be summarized range from short news with dozens of words to long reports with thousands of words. However, most existing NATS models are not good at summarizing long documents, due to the inherent limitations of their underlying neural architectures. In this paper, we focus on the task of long document summarization (LDS). Based on the inherent section structures of source documents, we divide an abstractive LDS problem into several smaller-sized problems. In this circumstance, how to provide a less-biased target summary as the supervision for each section is vital for the model’s performance. As a preliminary, we formally describe the section-to-summary-sentence (S2SS) alignment for LDS. Based on this, we propose a novel NATS framework for the LDS task. Our framework is built based on the theory of unbalanced optimal transport (UOT), and it is named as UOTSumm. It jointly learns three targets in a unified training objective, including the optimal S2SS alignment, a section-level NATS summarizer, and the number of aligned summary sentences for each section. In this way, UOTSumm directly learns the text alignment from summarization data, without resorting to any biased tool such as ROUGE. UOTSumm can be easily adapted to most existing NATS models. And we implement two versions of UOTSumm, with and without the pretrain-finetune technique. We evaluate UOTSumm on three publicly available LDS benchmarks: PubMed, arXiv, and GovReport. UOTSumm obviously outperforms its counterparts that use ROUGE for the text alignment. When combined with UOTSumm, the performance of two vanilla NATS models improves by a large margin. Besides, UOTSumm achieves better or comparable performance when compared with some recent strong baselines.

Progressive scene text erasing with self-supervision

Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data. Although data synthetic engines can provide vast amounts of annotated training samples, there are differences between synthetic and real-world data. In this paper, we employ self-supervision for feature representation on unlabeled real-world scene text images. A novel pretext task is designed to keep consistent among text stroke masks of image variants. We design the Progressive Erasing Network in order to remove residual texts. The scene text is erased progressively by leveraging the intermediate generated results which provide the foundation for subsequent higher quality results. Experiments show that our method significantly improves the generalization of the text erasing task and achieves state-of-the-art performance on public benchmarks.

Handwritten Text Classification Based on Convolutional Neural Network

The convolutional neural network (CNN) is a popular and highly effective deep learning technique for image classification. As the popularity of CNNs grew, the model has become popular in several machine learning problems. This paper utilizes a CNN model and the popular LeNet-5 transfer learned model to classify texts after the words are preprocessed and segmented from an image. The EMNIST database is used to train the models. The paper achieves an 89.36% validation accuracy on the EMNIST Balanced dataset and an 86.64% on the EMNIST By_Class dataset for the CNN model of four convolutional layers and one dense layer. Similarly, the LeNet-5 model obtained a validation accuracy of 85.88% on the EMNIST Balanced dataset and 85.01% accuracy on the EMNIST By_Class dataset. However, despite a higher accuracy in the EMNIST Balanced dataset, the EMNIST By_Class dataset achieves better results in real-world handwritten texts.

Omit needless words: Sentence length perception.

Short sentences improve readability. Short sentences also promote social justice through accessibility and inclusiveness. Despite this, much remains unknown about sentence length perception-an important factor in producing readable writing. Accordingly, we conducted a psychophysical study using procedures from Signal Detection Theory to examine sentence length perception in naive adults. Participants viewed real-world full-page text samples and judged whether a bolded target sentence contained more or fewer than 17 words. The experiment yielded four findings. First, naïve adults perceived sentence length in real-world text samples quickly (median = 300-400 ms) and precisely (median = ~90% correct). Second, flipping real-world text samples upside-down generated no reaction-time cost and nearly no loss in the precision of sentence length perception. This differs from the large inversion effects that characterize other highly practiced, real-world perceptual tasks involving canonically oriented stimuli, most notably face perception and reading. Third, participants significantly underestimated the length of mirror-reversed sentences-but not upside-down, nor standard sentences. This finding parallels participants' familiarity with commonly occurring left-justified right-ragged text, and suggests a novel demonstration of left-lateralized anchoring in scene syntax. Fourth, error patterns demonstrated that participants achieved their high speed, high precision sentence-length judgments by heuristically counting text lines, not by explicitly counting words. This suggests practical advice for writing instructors to offer students. When copy editing, students can quickly and precisely identify their long sentences via a line-counting heuristic, e.g., "a 17-word sentence spans about 1.5 text lines". Students can subsequently improve a long sentence's readability and inclusiveness by omitting needless words.

Meta-Information Fusion of Hierarchical Semantics Dependency and Graph Structure for Structured Text Classification

Structured text with plentiful hierarchical structure information is an important part in real-world complex texts. Structured text classification is attracting more attention in natural language processing due to the increasing complexity of application scenarios. Most existing methods treat structured text from a local hierarchy perspective, focusing on the semantics dependency and the graph structure of the structured text independently. However, structured text has global hierarchical structures with sophisticated dependency when compared to unstructured text. According to the variety of structured texts, it is not appropriate to use the existing methods directly. The function of distinction information within semantics dependency and graph structure for structured text, referred to as meta-information, should be stated more precisely. In this article, we propose HGMETA, a novel meta-information embedding frame network for structured text classification, to obtain the fusion embedding of hierarchical semantics dependency and graph structure in a structured text, and to distill the meta-information from fusion characteristics. To integrate the global hierarchical features with fused structured text information, we design a hierarchical LDA module and a structured text embedding module. Specially, we employ a multi-hop message passing mechanism to explicitly incorporate complex dependency into a meta-graph. The meta-information is constructed from meta-graph via neighborhood-based propagation to distill redundant information. Furthermore, using an attention-based network, we investigate the complementarity of semantics dependency and graph structure based on global hierarchical characteristics and meta-information. Finally, the fusion embedding and the meta-information can be straightforwardly incorporated for structured text classification. Experiments conducted on three real-world datasets show the effectiveness of meta-information and demonstrate the superiority of our method.

The Entropy of Digital Texts-The Mathematical Background of Correctness.

Based on Shannon's communication theory, in the present paper, we provide the theoretical background to finding an objective measurement-the text-entropy-that can describe the quality of digital natural language documents handled with word processors. The text-entropy can be calculated from the formatting, correction, and modification entropy, and based on these values, we are able to tell how correct or how erroneous digital text-based documents are. To present how the theory can be applied to real-world texts, for the present study, three erroneous MS Word documents were selected. With these examples, we can demonstrate how to build their correcting, formatting, and modification algorithms, to calculate the time spent on modification and the entropy of the completed tasks, in both the original erroneous and the corrected documents. In general, it was found that using and modifying properly edited and formatted digital texts requires less or an equal number of knowledge-items. In information theory, it means that less data must be put on the communication channel than in the case of erroneous documents. The analysis also revealed that in the corrected documents not only the quantity of the data is less, but the quality of the data (knowledge pieces) is higher. As the consequence of these two findings, it is proven that the modification time of erroneous documents is severalfold of the correct ones, even in the case of minimal first level actions. It is also proven that to avoid the repetition of the time- and resource-consuming actions, we must correct the documents before their modification.

A novel medical text classification model with Kalman filter for clinical decision making

Medical text classification has long been a challenging issue in the construction of clinical decision support systems because medical texts contain medical terminologies and various medical abbreviations. This paper proposes an ALBERT-based fusion Kalman-filter model, named AFKF, to address word-level and sentence-level noises in electronic medical records. Specifically, a sliding window scheme is explored to deal with the coupling relationship among large sequences. Furthermore, we design a fusion block on the basis of Kalman filter to integrate representations of multiple segment sequences. Experiments indicate that our approach significantly outperforms the baseline methods with real-world medical texts. Our fusion strategy also improves the performance of other feature classification models in the medical text classification task.

Intention-guided deep semi-supervised document clustering via metric learning

The intention expresses the user’s preference for document structure division. Intention-guided document structure division is an important task in the field of text mining. To achieve this goal, deep semi-supervised document clustering provides a promising solution to personalized document clustering. However, traditional deep semi-supervised clustering models suffer from the problem of the limited number of constraints which is insufficient for intention-guided document clustering. Moreover, documents normally have various emphases on their representations to reflect different structural opinions. In this paper, we proposed an intention-guided deep semi-supervised document clustering model, namely IGSC, to divide document structure based on a small amount of user-provided supervised information. IGSC designs a deep metric learning network to solve the above problems. The deep metric learner explores the user’s global intention and outputs an intention matrix. The intention is explored from the small amount user provided pairwise constraints and is used to guide the representation learning. Moreover, IGSC uses the intention matrix to guide the clustering process, to get the clustering results that best meet the user’s intention. This paper compares IGSC with a number of document clustering models on four real-world text datasets, namely Reu-10k, BBC, ACM, and Abstract. The results show that IGSC evidently improves the clustering performance and outperforms the best result of benchmark models with 7% on average. The comparison with other models and the visualization results can demonstrate that IGSC is effective.

The Real-World Experiences of Persons With Multiple Sclerosis During the First COVID-19 Lockdown: Application of Natural Language Processing.

The increasing availability of "real-world" data in the form of written text holds promise for deepening our understanding of societal and health-related challenges. Textual data constitute a rich source of information, allowing the capture of lived experiences through a broad range of different sources of information (eg, content and emotional tone). Interviews are the "gold standard" for gaining qualitative insights into individual experiences and perspectives. However, conducting interviews on a large scale is not always feasible, and standardized quantitative assessment suitable for large-scale application may miss important information. Surveys that include open-text assessments can combine the advantages of both methods and are well suited for the application of natural language processing (NLP) methods. While innovations in NLP have made large-scale text analysis more accessible, the analysis of real-world textual data is still complex and requires several consecutive steps. We developed and subsequently examined the utility and scientific value of an NLP pipeline for extracting real-world experiences from textual data to provide guidance for applied researchers. We applied the NLP pipeline to large-scale textual data collected by the Swiss Multiple Sclerosis (MS) registry. Such textual data constitute an ideal use case for the study of real-world text data. Specifically, we examined 639 text reports on the experienced impact of the first COVID-19 lockdown from the perspectives of persons with MS. The pipeline has been implemented in Python and complemented by analyses of the "Linguistic Inquiry and Word Count" software. It consists of the following 5 interconnected analysis steps: (1) text preprocessing; (2) sentiment analysis; (3) descriptive text analysis; (4) unsupervised learning-topic modeling; and (5) results interpretation and validation. A topic modeling analysis identified the following 4 distinct groups based on the topics participants were mainly concerned with: "contacts/communication;" "social environment;" "work;" and "errands/daily routines." Notably, the sentiment analysis revealed that the "contacts/communication" group was characterized by a pronounced negative emotional tone underlying the text reports. This observed heterogeneity in emotional tonality underlying the reported experiences of the first COVID-19-related lockdown is likely to reflect differences in emotional burden, individual circumstances, and ways of coping with the pandemic, which is in line with previous research on this matter. This study illustrates the timely and efficient applicability of an NLP pipeline and thereby serves as a precedent for applied researchers. Our study thereby contributes to both the dissemination of NLP techniques in applied health sciences and the identification of previously unknown experiences and burdens of persons with MS during the pandemic, which may be relevant for future treatment.