Text Representation Research Articles

Location-enhanced syntactic knowledge for biomedical relation extraction

Biomedical relation extraction has long been considered a challenging task due to the specialization and complexity of biomedical texts. Syntactic knowledge has been widely employed in existing research to enhance relation extraction, providing guidance for the semantic understanding and text representation of models. However, the utilization of syntactic knowledge in most studies is not exhaustive, and there is often a lack of fine-grained noise reduction, leading to confusion in relation classification. In this paper, we propose an attention generator that comprehensively considers both syntactic dependency type information and syntactic position information to distinguish the importance of different dependency connections. Additionally, we integrate positional information, dependency type information, and word representations together to introduce location-enhanced syntactic knowledge for guiding our biomedical relation extraction. Experimental results on three widely used English benchmark datasets in the biomedical domain consistently outperform a range of baseline models, demonstrating that our approach not only makes full use of syntactic knowledge but also effectively reduces the impact of noisy words.

Automatic Detection of Verbal Deception in Romanian With Artificial Intelligence Methods

Automatic deception detection is an important task with several applications in both direct physical human communication, as well as in computer-mediated one. The objective of this paper is to study the nature of deceptive language. The primary goal of this study is to investigate deception in Romanian written communication. We created a number of artificial intelligence models (based on Support Vector Machine, Random Forest, and Artificial Neural Network) to detect dishonesty in a topic-specific corpus. To assess the efficiency of the Linguistic Inquiry and Word Count (LIWC) categories in Romanian, we conducted a comparison between multiple text representations based on LIWC, TF-IDF, and LSA. The results show that in the case of datasets with a common subject such as the one we used regarding friendship, text categorization is more successful using general text representations such as TF-IDF or LSA. The proposed approach achieves an accuracy of the classification of 91.3%, outperforming the similar approaches presented in the literature. These findings have implications in fields like linguistics and opinion mining, where research on this subject in languages other than English is necessary. Keywords: Deception Detection, Text Classification, Natural Language Processing, Machine Learning.

A Multi-Scale Natural Scene Text Detection Method Based on Attention Feature Extraction and Cascade Feature Fusion.

Scene text detection is an important research field in computer vision, playing a crucial role in various application scenarios. However, existing scene text detection methods often fail to achieve satisfactory results when faced with text instances of different sizes, shapes, and complex backgrounds. To address the challenge of detecting diverse texts in natural scenes, this paper proposes a multi-scale natural scene text detection method based on attention feature extraction and cascaded feature fusion. This method combines global and local attention through an improved attention feature fusion module (DSAF) to capture text features of different scales, enhancing the network's perception of text regions and improving its feature extraction capabilities. Simultaneously, an improved cascaded feature fusion module (PFFM) is used to fully integrate the extracted feature maps, expanding the receptive field of features and enriching the expressive ability of the feature maps. Finally, to address the cascaded feature maps, a lightweight subspace attention module (SAM) is introduced to partition the concatenated feature maps into several sub-space feature maps, facilitating spatial information interaction among features of different scales. In this paper, comparative experiments are conducted on the ICDAR2015, Total-Text, and MSRA-TD500 datasets, and comparisons are made with some existing scene text detection methods. The results show that the proposed method achieves good performance in terms of accuracy, recall, and F-score, thus verifying its effectiveness and practicality.

CogAware: Cognition-Aware framework for sentiment analysis with textual representations

Sentiment analysis has become an important research area in artificial intelligence. Recently, the integration of sentiment analysis with cognitive neuroscience in natural language processing (NLP) tasks has attracted widespread attention. Cognitive signals and textual signals (i.e. word embeddings) both contain distinctive information for sentiment analysis tasks. However, most previous studies cannot effectively capture the specific features and cross-domain features while integrating cognitive signals acquired from brain activity and textual signals obtained from natural language processing (NLP). To address this issue, we propose CogAware, which learns to obtain a deep representation that combines purified specific features with cross-domain features from textual and cognitive signals. CogAware employs four private encoders to extract specific or cross-domain features from textual and cognitive signals alternately. It also employs feature reinforcement and orthogonality regularization to separate specific and cross-domain features from each modality. Moreover, a shared encoder and a modality discriminator are used to further capture cross-domain features from different modalities. Our designed architecture utilizes cognitive signals and word embeddings during model training, yet relies solely on word embeddings for model inference. Experiments on a public dataset show that CogAware achieves new state-of-the-art performance on the sentiment analysis task compared with other existing models. The source code of CogAware is available at: https://github.com/zhejiangzhuque/CogAware.

Unified multimodal fusion transformer for few shot object detection for remote sensing images

Object detection is a fundamental computer vision task with wide applications in remote sensing, but traditional methods strongly rely on large annotated datasets which are difficult to obtain, especially for novel object classes. Few-shot object detection (FSOD) aims to address this by using detectors to learn from very limited labeled data. Recent work fuse multi-modalities like image–text pairs to tackle data scarcity but require external region proposal network (RPN) to align cross-modal pairs which leads to a bias towards base classes and insufficient cross-modal contextual learning. To address these problems, we propose a unified multi-modal fusion transformer (UMFT), which extracts visual features from ViT and textual encodings from BERT to align multi-modal representations in an end-to-end manner. Specifically, affinity-guided fusion (AFM) captures semantically related image–text pairs by modeling their affinity relationships to selectively combine most informative pairs. In addition, cross-modal correlation module (CCM) captures discriminative inter-modal patterns between image and text representations and filters out unrelated features to enhance cross-modal alignment. By leveraging AFM to focus on semantic relationships and CCM to refine inter-modal features, the model better aligns multimodal data without RPN. These representations are passed to detection decoder that predicts bounding boxes, probabilities of class and cross-modal attributes. Evaluation of UMFT on benchmark datasets NWPU VHR-10 and DIOR demonstrated its ability to leverage limited image–text training data via dynamic fusion, achieving new state-of-the-art mean average precision (mAP) for few-shot object detection. Our code will be publicly available at https://github.com/abdullah-azeem/umft.

Genre Classification of Books in Russian with Stylometric Features: A Case Study

Within the literary domain, genres function as fundamental organizing concepts that provide readers, publishers, and academics with a unified framework. Genres are discrete categories that are distinguished by common stylistic, thematic, and structural components. They facilitate the categorization process and improve our understanding of a wide range of literary expressions. In this paper, we introduce a new dataset for genre classification of Russian books, covering 11 literary genres. We also perform dataset evaluation for the tasks of binary and multi-class genre identification. Through extensive experimentation and analysis, we explore the effectiveness of different text representations, including stylometric features, in genre classification. Our findings clarify the challenges present in classifying Russian literature by genre, revealing insights into the performance of different models across various genres. Furthermore, we address several research questions regarding the difficulty of multi-class classification compared to binary classification, and the impact of stylometric features on classification accuracy.

Machine learning-enabled hybrid intrusion detection system with host data transformation and an advanced two-stage classifier

Network Intrusion Detection Systems (NIDS) have been extensively investigated by monitoring real network traffic and analyzing suspicious activities. However, there are limitations in detecting specific types of attacks with NIDS, such as Advanced Persistent Threats (APT). Additionally, NIDS is restricted in observing complete traffic information due to encrypted traffic or a lack of authority. To address these limitations, a Host-based Intrusion Detection system (HIDS) evaluates resources in the host, including logs, files, and folders, to identify APT attacks that routinely inject malicious files into victimized nodes. In this study, a hybrid network intrusion detection system that combines NIDS and HIDS is proposed to improve intrusion detection performance. The host data undergoes a Language Processing (NLP)-based Bidirectional Encoder Representations from Transformers (BERT) model from textual representation to a numerical one in order to process host data in a similar way to the network flow data through machine learning models. The feature flattening technique is applied to flatten two-dimensional host-based features that is provided by BERT into one-dimensional vectors so that host-based and network flow-based features can be processed by advanced Machine Learning (ML) models. In order to enhance HIDS effectiveness, a two-stage collaborative classifier is utilized, which applies two tiers of machine learning algorithms, binary and multi-class classifiers, to detect network intrusions. Once a binary classifier is used to detect benign samples to reduce the complexity of the original problem, the attack data are classified by a multi-class supervised learner to identify attack types. Hence, the overall performance of the two-stage collaborative model outperforms the baseline classifier, XGBoost. The proposed method is shown to generalize across two well-known datasets, CICIDS 2018 and NDSec-1. The performance of XGBoost, which represents conventional ML, is evaluated. Combining host and network features enhances attack detection performance (macro average F1 score) by 8.1% under the CICIDS 2018 dataset and 3.7% under the NDSec-1 dataset. Meanwhile, the two-stage collaborative classifier improves detection performance for most single classes, especially for DoS-LOIC-UDP and DoS-SlowHTTPTest, with improvements of 30.7% and 84.3%, respectively, when compared with the traditional ML models.

Exploring climate change discourse on social media and blogs using a topic modeling analysis

Climate change is one of the most pressing global issues of our time, and understanding public perception and awareness of the topic is crucial for developing effective policies to mitigate its effects. While traditional survey methods have been used to gauge public opinion, advances in natural language processing (NLP) and data visualization techniques offer new opportunities to analyze user-generated content from social media and blog posts. In this study, a new dataset of climate change-related texts was collected from social media sources and various blogs. The dataset was analyzed using BERTopic and LDA to identify and visualize the most important topics related to climate change. The study also used sentence similarity to determine the similarities in the comments written and which topic categories they belonged to. The performance of different techniques for keyword extraction and text representation, including OpenAI, Maximal Marginal Relevance (MMR), and KeyBERT, was compared for topic modeling with BERTopic. It was seen that the best coherence score and topic diversity metric were obtained with OpenAI-based BERTopic. The results provide insights into the public's attitudes and perceptions towards climate change, which can inform policy development and contribute to efforts to reduce activities that cause climate change.

Video text rediscovery: Predicting and tracking text across complex scenes

AbstractDynamic texts in scene videos provide valuable insights and semantic cues crucial for video applications. However, the movement of this text presents unique challenges, such as blur, shifts, and blockages. While efficient in tracking text, state‐of‐the‐art systems often need help when text becomes obscured or complicated scenes. This study introduces a novel method for detecting and tracking video text, specifically designed to predict the location of obscured or occluded text in subsequent frames using a tracking‐by‐detection paradigm. Our approach begins with a primary detector to identify text within individual frames, thus enhancing tracking accuracy. Using the Kalman filter, Munkres algorithm, and deep visual features, we establish connections between text instances across frames. Our technique works on the concept that when text goes missing in a frame due to obstructions, we use its previous speed and location to predict its next position. Experiments conducted on the ICDAR2013 Video and ICDAR2015 Video datasets confirm our method's efficacy, matching or surpassing established methods in performance.

Howdy Comrade

Abstract American and Western audiences have long come to understand Soviet and Russian womanhood, and thus US womanhood, from representations in popular televisual texts. While there is a long history of popular culture presenting the “othered” women of Eastern Europe, for example as temptress “Bond girls” during the Cold War, these narratives have continued onscreen into the twenty-first century. We examine the myriad representations from both the Cold War and post-Cold War period, noting the typical narrative constructions that focus on femme fatales, psychological and sexual trauma, and economic precarity, and how these have continued in contemporary popular culture to shore up notions of Western cultural and political superiority. The characters and the situations in which they find themselves, as spies, assassins, and double agents, continue to send messages about danger and dominance regarding both gender and geopolitics.

Tales of (Under)Representation: Afro-Latinx in Spanish as a Heritage Language Textbooks

Abstract: The present study examines the lack of representation of minority communities in the existing literature by examining the representation of Afro-Latinxs in texts and visuals in seven Spanish as a Heritage Language (SHL) textbooks, and the ideologies behind these representations. Drawing upon Norman Fairclough's (1995) model for conducting Critical Discourse Analysis (CDA) and Gunther Kress and Theo van Leeuwen's (2001, 2006) grammar of visual design, this current study analyzes text (readings, descriptions, labels, among others) and visuals (people, pictures, buildings, artifacts, among others) in these textbooks. The findings suggest that Afro-Latinx are hardly represented in SHL textbooks. There were only 38 textual representations in the seven SHL textbooks examined and only 18 images clearly referencing Afro-Latinx. This underrepresentation is in line with the ideology of erasure. In addition, ideologies of collectivization and tourism discourse were found throughout the textbooks analyzed. The present study's findings confirm the invisibility of Afro-Latinx in educational discourse and emphasizes the need to examine representations in Spanish language textbooks and teaching materials.

Progressive Multigranularity Information Propagation for Coupled Aspect-Opinion Extraction.

Coupled aspect-opinion extraction aims to identify aspect-opinion pairs in the form of (aspect term, opinion term) or triplets in the form of (aspect term, opinion term, sentiment polarity) from user-generated texts. Compared to the traditional aspect-based sentiment prediction or extraction tasks, coupled aspect-opinion extraction needs to associate aspects with their corresponding opinions and organize opinion-related information into structured outputs. The existing works either divide this task into subproblems (i.e., term extraction and relation prediction) or utilize a unified tagging scheme. However, these methods only focus on atomic word-level interactions and ignore the intensive information propagation among different granularities (e.g., words and word pairs). To address this limitation, we propose a progressive multigranularity information propagation network that progressively explores three types of correlations with different granularities. Specifically, our model starts with the most basic word-level correlations by composing all possible word pairs. In the second stage, the pairwise relation information is used to update the word features. The last stage propagates information among word pairs to produce the relation scores. We treat the task as a unified relation prediction problem and construct an end-to-end framework that iteratively conducts the three-stage information propagation to refine the textual representations. Comprehensive experiments on different aspect-based sentiment analysis benchmarks clearly demonstrate the effectiveness of the proposed approach.

Towards a disease prediction system: BioBERT-based medical profile representation

<p>Healthcare professionals are increasingly interested in predicting diseases before they manifest, as this can prevent more serious health conditions and even save lives. Machine learning techniques are now playing an important role in healthcare, including in the early prediction of diseases based on prior medical knowledge. However, one of the biggest challenges is how to represent medical information in a way that can be processed by machine learning algorithms. Medical histories are often in a format that computers cannot read, so filtering and converting this information into numerical representations is a crucial step. This process has become easier with the advancement of natural language processing techniques. In this paper, we propose three representations of medical information, two of which are based on BioBERT, the latest text representation techniques for the biomedical sector. The efficiency of these representations is tested on the MIMIC-III database, which contains information on 46,520 patients. The focus of the study is on predicting Coronary Artery Disease, and the results demonstrate the effectiveness of the proposed approach. The study highlights the importance of medical history in disease prediction and demonstrates the potential of machine learning techniques to advance healthcare.</p>

Exploration of Self-Efficacy Based on Students' Mathematical Representation Ability In Problem Solving SPLDV

Aim for know ability representation mathematical in finish questions on the material system linear equations of two variables (SPLDV) are reviewed of student self-efficacy class VIII SMPN 1 Praya Timur. As for Sujek in study This consists of 3 of 28 students class VIII which has categories of high self-efficacy, medium self-efficacy and low self-efficacy. Types of research This is study qualitative descriptive. Instruments used​ in study This is questionnaire, question test ability representation mathematics and guidelines interview. Procedure data collection used in study This that is documentation and interviews. Data analysis techniques were carried out with method reducing data, presenting data, and interesting conclusion. Checking validity of the data used triangulation technique. Research result show that ability representation mathematical student class VIII SMPN 1 Praya Timur is divided into 3 (three) categories, namely student with high self-efficacy category capable shows 3 aspects ability representation mathematical that is visual representation, representation equality or expression mathematics, and representation of words or text written, whereas student with moderate self-efficacy category only capable shows 2 aspects ability representation mathematical that is representation equality or expression mathematics, and representation of words or text written. Temporary That student with low self-efficacy category only Can shows 1 aspect ability representation mathematical that is representation equality or expression mathematical.

Silent Signals to Spoken Words: A Sign Language Conversion to Text and Speech

Abstract: By leveraging machine learning, an innovative system has emerged to connect sign language with text-to-speech capabilities. Powered by sophisticated algorithms, this pioneering solution conversion of visual expressions into textual representations and then vocalizes it into spoken words. This fusion of technology stans as a transformative asset, facilitating seamless communication for individuals facing hearing impairments. By dismantling obstacles, this advancement fosters inclusive and accessible interactions, ultimately elevating the standard of living for members of the hearing- impaired population

A multifaceted architecture to Automate Essay Scoring for assessing english article writing: Integrating semantic, thematic, and linguistic representations

We propose a multifaceted architecture for automated essay scoring integrating semantic, thematic, and linguistic representations. Specifically, for the deep semantic content of the essay, we employ Convolutional Neural Network (ConvNet) and attention mechanism module to extract local semantic representation, and use ConvNet, Long Short-Term Memory network (LSTM), and attention mechanism module to capture the global semantic representation, providing the comprehensive deep semantic-facet representations. To answer the presence of prompt in the test essay, we utilize the Doc2Vec model to represent the target essay and the essay prompt as vectors and calculate their textual similarity as thematic-facet representations. In addition, we construct six categories of nine manual features, including grammatical errors, essay length, textual complexity, word complexity, sentence complexity, and the number of clauses, to capture the shallow linguistic representation that deep learning models may struggle to uncover. Finally, we integrate the multifaceted representation through the fully connected layer to automatically score essays. Experimental results on the standard public dataset ASAP and the more complex dataset CLC-FCE, which varies in standards, lengths, and topics, demonstrate that the proposed method effectively captures diverse aspects of textual representations. For the ASAP dataset, our method reduced the training time to 1862 s per essay and the inference time to 0.9778 s, achieving a 1.13 improvement in the Quadratic Weighted Kappa score over the previous best method. On the CLC-FCE dataset, our approach enhanced the Pearson's product-moment correlation coefficient and Spearman's rank correlation coefficient by 0.005 and 0.0337 respectively, surpassing prior benchmarks.

Enhancing traditional Chinese medical named entity recognition with Dyn-Att Net: a dynamic attention approach

Our study focuses on Traditional Chinese Medical (TCM) named entity recognition (NER), which involves identifying and extracting specific entity names from TCM record. This task has significant implications for doctors and researchers, as it enables the automated identification of relevant TCM terms, ultimately enhancing research efficiency and accuracy. However, the current Bidirectional Encoder Representations from Transformers-Long Short Term Memory-Conditional Random Fields (BERT-LSTM-CRF) model for TCM NER is constrained by a traditional structure, limiting its capacity to fully harness the advantages provided by Bidirectional Encoder Representations from Transformers (BERT) and long short term memory (LSTM) models. Through comparative experiments, we also observed that the straightforward superimposition of models actually leads to a decrease in recognition results. To optimize the structure of the traditional BERT-BiLSTM-CRF model and obtain more effective text representations, we propose the Dyn-Att Net model, which introduces dynamic attention and a parallel structure. By integrating BERT and LSTM models with the dynamic attention mechanism, our model effectively captures semantic, contextual, and sequential relations within text sequences, resulting in high accuracy. To validate the effectiveness of our model, we compared it with nine other models in TCM dataset namely the publicly available PaddlePaddle dataset. Our Dyn-Att Net model, based on BERT, outperforms the other models, achieving an F1 score of 81.91%, accuracy of 92.06%, precision of 80.26%, and recall of 83.76%. Furthermore, its robust generalization capability is substantiated through validation on the APTNER, MSRA, and EduNER datasets. Overall, the Dyn-Att Net model not only enhances NER accuracy within the realm of traditional Chinese medicine, but also showcases considerable potential for cross-domain generalization. Moreover, the Dyn-Att Net model’s parallel architecture facilitates efficient computation, contributing to time-saving efforts in NER tasks.

FarmTechBot (FTB): Empowering farmers for better harvest

In an evolving world, the FarmTechBot (FTB) emerges as a pioneering digital assistant, empowering farmers with essential insights and real-time information crucial for optimizing agricultural practices. The presence of chatbot functionality capable of addressing queries related to soil, pest, and market linkage associates to overcome hurdles for users seeking real-time information. Furthermore, the lack of voice recognition capabilities limits accessibility, especially for users who prefer or require voice-based interaction. Additionally, the manual process of pest identification from uploaded crop images hampers efficiency, prolonging the time required for pest management. The FTB represents a significant advancement in agricultural technology, addressing the existing system's limitations and empowering farmers with real-time information, enhanced accessibility, and streamlined pest management capabilities. The FTB utilizes a combination of techniques including Histogram of Oriented Gradients (HOG) for image feature extraction and classification using Support Vector Classifier (SVC). In Natural Language Processing (NLP), it employs tokenization and TF-IDF vectorization for text preprocessing and representation, alongside Linear Support Vector Classifier (LinearSVC) for intent classification.

Few-shot intent detection with self-supervised pretraining and prototype-aware attention

Few-shot intent detection is a more challenging application. However, traditional prototypical networks based on averaging often suffer from issues such as missing key information, poor generalization capabilities. In previous work, using three-dimensional convolutional neural networks (3DCNN) to generate prototype representations faces challenges with long-distance dependencies. Furthermore, a pretrained encoder’s performance in a specific domain is often suboptimal because its knowledge of the specific domain is fragmented. Therefore, in this paper, we propose a simple yet effective two-stage learning strategy to address these issues. In the first stage, we propose a self-supervised multi-task pretraining (SMTP) strategy. SMTP utilizes unlabeled data from the current domain to help the pretrained encoder learn the semantic information of the text and implicitly distinguish semantically similar text representations without using any labels. SMTP aims to enhance the representation capability of the pretrained encoder in a specific domain. In the second stage, we propose a prototype-aware attention (PaAT) model to generate prototype representations of the same class. PaAT generates prototype representations by calculating the attention between class texts, which can effectively solve the long-distance dependence problem of 3DCNN. PaAT is a siamese architecture that can simultaneously generate prototype representations and sentence-level representations of unseen data. In addition, to prevent overfitting in few-shot learning, we introduce an unsupervised contrastive regularization term to constrain PaAT. Our method achieves state-of-the-art performance on four public datasets.11Our code is available: https://github.com/YS19999/SMTP-PaAT. .

M3KGR: A momentum contrastive multi-modal knowledge graph learning framework for recommendation

In recent years, there has been a discernible upswing in the utilization of knowledge graphs within recommender systems. This heightened interest in knowledge graphs stems from their ability to vividly illustrate relationships between items through augmented attribute representations. Scholars have endeavored to incorporate multi-modal data, encompassing texts and images, into knowledge graphs, albeit with restricted success. These efforts primarily hinge on image models for extracting visual representations and text models for extracting textual representations, prompting apprehensions regarding potential disparities between the two modalities. Moreover, the current approaches for computing node similarities using multi-modal information have not witnessed noteworthy progress or enhancements.Momentum Contrastive Multi-Modal Knowledge Graph Learning Framework for Recommendation (M3KGR) proposed in this paper aims to enhance the utilization of multi-modal data. Specifically, we leverage the existing CLIP model to simultaneously extract textual and visual representations of an entity, thus overcoming the challenge of integrating multi-modal information. Additionally, we introduce a multi-modal enhanced attention technique to further enhance the performance of the graph attention network. Furthermore, we introduce Momentum Contrast to mitigate the common issues of data sparsity and noise in recommender systems. Our comprehensive experiments conducted on three real datasets demonstrate that our model enhances the efficacy of multi-modal knowledge graphs in recommender systems by fully leveraging the potential of multi-modal data. The implementation of our model will be available at https://github.com/KlaineWei/M3KGR.