Article
Psychology, Multidisciplinary
Xingsan Chai, Jie Bao
Summary: The study examines how linguistic differences between Chinese and learners' native language affect the acquisition of Chinese characters, vocabulary, and grammar. It finds that closer linguistic distance between languages facilitates better acquisition, but this effect diminishes as Chinese proficiency improves.
FRONTIERS IN PSYCHOLOGY
(2023)
Article
Computer Science, Information Systems
Dezhi Peng, Lianwen Jin, Weihong Ma, Canyu Xie, Hesuo Zhang, Shenggao Zhu, Jing Li
Summary: This study proposes a novel segmentation-based method for recognizing handwritten Chinese text using a simple yet efficient fully convolutional network. A new weakly supervised learning method is introduced to train the network using only transcript annotations, avoiding the need for expensive character segmentation annotations. Additionally, a contextual regularization method is proposed to integrate contextual information into the network during training, resulting in improved recognition performance. Extensive experiments on four widely used benchmarks demonstrate that our method surpasses existing methods in both online and offline handwritten Chinese text recognition, while also achieving higher inference speed than CTC/attention-based approaches.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Dezhi Peng, Lianwen Jin, Yuliang Liu, Canjie Luo, Songxuan Lai
Summary: Handwritten Chinese text recognition (HCTR) is an active research area, but most previous studies only focus on recognition of cropped text line images and ignore the errors caused by text line detection in real-world applications. This study proposes PageNet, an end-to-end weakly supervised page-level HCTR model that detects and recognizes characters and predicts reading order between them. PageNet is able to handle complex layouts, including multi-directional and curved text lines, and requires only transcripts for real data annotation, avoiding the cost of labeling bounding boxes. Experimental results on five datasets show PageNet's superiority over existing weakly supervised and fully supervised page-level methods.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Artificial Intelligence
Song Deng, Qianliang Li, Renjie Dai, Siming Wei, Di Wu, Yi He, Xindong Wu
Summary: In this paper, we propose a Chinese text classification algorithm based on deep active learning for the power system, which addresses the challenge of specialized text classification. By applying a hierarchical confidence strategy, our model achieves higher classification accuracy with fewer labeled training data.
APPLIED SOFT COMPUTING
(2024)
Article
Computer Science, Artificial Intelligence
Jose Antonio Garcia-Diaz, Salud Maria Jimenez-Zafra, Miguel Angel Garcia-Cumbreras, Rafael Valencia-Garcia
Summary: The rise of social networks has allowed individuals with misogynistic, xenophobic, and homophobic views to spread hate-speech, causing harm to individuals or groups based on their gender, ethnicity, or sexual orientation. Automatic identification of hate-speech is challenging, especially in languages other than English. This study focuses on identifying hate-speech in Spanish and examines the most effective features and their combination for developing accurate systems.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Chemistry, Multidisciplinary
Yee Fan Tan, Tee Connie, Michael Kah Ong Goh, Andrew Beng Jin Teoh
Summary: The proposed handwritten text recognition pipeline effectively locates and recognizes text, and identifies the context of the text. Clinical receipts were used as the subjects of study.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Lei Kang, Pau Riba, Marcal Rusinol, Alicia Fornes, Mauricio Villegas
Summary: This paper introduces a novel method that bypasses recurrence during the training process using transformer models for handwriting recognition. By utilizing multi-head self-attention layers, the model is able to handle character recognition and learn the language-related dependencies of character sequences to be decoded. The model is capable of recognizing out-of-vocabulary words.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Weiqiang Jin, Biao Zhao, Liwen Zhang, Chenxing Liu, Hang Yu
Summary: Aspect-based Sentiment Analysis (ABSA) is an important research field in natural language understanding (NLU), aiming to accurately recognize reviewers' opinions on different aspects of products and services. However, mainstream ABSA approaches rely heavily on large-scale supervised datasets, making it challenging to generalize high-quality sentiment analysis models. To address this, we propose a novel knowledge augmentation framework, called DictABSA, which leverages external background knowledge to enhance ABSA performance.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Sunjae Kwon, Dongsuk Oh, Youngjoong Ko
Summary: A novel knowledge-based word-sense disambiguation system is introduced in this study, which significantly enhances the performance by using word vector representation and word similarity analysis.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Computer Science, Interdisciplinary Applications
Yindi Sun, Wei Liu, Guozhong Cao, Qingjin Peng, Jianjie Gu, Jiaming Fu
Summary: Patent documents are crucial sources of knowledge for engineering design. However, existing patent analysis methods face challenges in extracting design knowledge from patent databases due to language differences. This paper introduces a new approach that uses natural language processing techniques to build a patent design knowledge graph for extracting useful design information from Chinese patent texts. The proposed method is validated using randomly selected patent texts and tested for the design of a new storage device for patentability.
COMPUTERS IN INDUSTRY
(2022)
Article
Computer Science, Artificial Intelligence
Xiao Pu, Lin Yuan, Jiaxu Leng, Tao Wu, Xinbo Gao
Summary: This study proposes a method that integrates external lexical knowledge to improve text matching by modeling the senses of potentially ambiguous words. A lightweight word sense disambiguation (WSD) model based on BERT and WordNet is designed and integrated into a matching mechanism. Experimental results on three matching-based tasks show that the sense knowledge-enhanced matching mechanism outperforms BERT-based baselines and other recent approaches.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Shuying Hu, Qiufeng Wang, Kaizhu Huang, Min Wen, Frans Coenen
Summary: This paper proposes a novel approach to address the language model issue in handwritten text recognition. By utilizing internet content and dynamically generating an adaptive language model, improved recognition performance is achieved.
INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION
(2023)
Article
Multidisciplinary Sciences
Dean Schillinger, Nicholas D. Duran, Danielle S. McNamara, Scott A. Crossley, Renu Balyan, Andrew J. Karter
Summary: Research shows that clinicians adapting their communication to match patients' health literacy helps promote shared understanding and equity, with universal tailoring strategy associated with better understanding and universal precautions not. Adaptability in physician communication is beneficial for patients' health literacy.
Article
Chemistry, Multidisciplinary
Urszula Krzeszewska, Aneta Poniszewska-Maranda, Joanna Ochelska-Mierzejewska
Summary: This study compared different text vectorization methods in natural language processing, especially in Text Mining, by checking the accuracy of classification. The methods NBC and k-NN were used to avoid the influence of method choice on the final result, providing a basis for further research in better automatic text analysis.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Software Engineering
Sara Melotte, Filip Ilievski, Linglan Zhang, Aditya Malte, Namita Mutha, Fred Morstatter, Ninareh Mehrabi
Summary: It has been found that bias exists in common sense knowledge bases and models. The study investigates the source of bias in a knowledge model called COMET by training it on different combinations of language models and knowledge bases. Bias is measured using sentiment and regard as proxies, and analyzed through three methods: overgeneralization and disparity, keyword outliers, and relational dimensions. The results show that larger models are more nuanced in their biases but can be more biased than smaller models in certain categories (e.g. utility of religions), which is attributed to the larger knowledge accumulated during pretraining. It is also observed that training on a larger set of common sense knowledge often leads to more bias, and that models generally have stronger negative regard than positive.
IEEE INTERNET COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Mohammad AL-Smadi, Mahmoud M. Hammad, Sa'ad A. Al-Zboon, Saja AL-Tawalbeh, Erik Cambria
Summary: The increasing interactive content in the Internet has led to research on Aspect-Based Sentiment Analysis (ABSA) in order to understand sentiments and aspects of a product in user comments. A deep learning model based on Gated Recurrent Units (GRU) and features extracted using the Multilingual Universal Sentence Encoder (MUSE) was developed for aspect extraction and polarity classification. The proposed Pooled-GRU model achieved high F1 scores of 93.0% for aspect extraction and 90.86% for aspect polarity classification, outperforming the baseline model and related research methods.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Seham Basabain, Erik Cambria, Khalid Alomar, Amir Hussain
Summary: An increasing number of studies are using pre-trained language models to tackle few/zero-shot text classification problems. However, most of these studies fail to consider the semantic information embedded in the natural language class labels. This work demonstrates how label information can be leveraged to enhance feature representation in input texts, particularly in scenarios with scarce data resources and short texts lacking semantic information like tweets. The study also shows the effectiveness of zero-shot implementation in predicting new classes across different domains, achieving high accuracy in Arabic sarcasm detection.
Article
Computer Science, Artificial Intelligence
Kai He, Yucheng Huang, Rui Mao, Tieliang Gong, Chen Li, Erik Cambria
Summary: This paper proposes a virtual prompt pre-training method that incorporates the virtual prompt into PLM parameters to achieve entity-relation-aware pre-training. The proposed method provides robust initialization for prompt encoding and avoids the labor-intensive and subjective issues in label word mapping and prompt template engineering.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mostafa Amin, Erik W. Cambria, Bjorn Schuller
Summary: ChatGPT demonstrates the potential of general artificial intelligence capabilities and performs well across various natural language processing tasks. This study evaluates ChatGPT's text classification abilities for affective computing problems including personality prediction, sentiment analysis, and suicide tendency detection. Results show that task-specific RoBERTa models generally outperform other baselines, while ChatGPT performs decently and is comparable to Word2Vec and BoW baselines. ChatGPT exhibits robustness against noisy data, outperforming Word2Vec in such scenarios. The study concludes that ChatGPT is a good generalist model but not as specialized as task-specific models for optimal performance.
IEEE INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mauajama Firdaus, Asif Ekbal, Erik Cambria
Summary: This research proposes a multilingual multitask approach that improves intent accuracy and slot filling for three different languages. The experimental results show an improvement in both tasks for all languages.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Jintao Wen, Dazhi Jiang, Geng Tu, Cheng Liu, Erik Cambria
Summary: Multimodal data is crucial for enhanced emotion recognition in conversation, but effectively fusing different modal features to understand contextual information is challenging. This work proposes a Dynamic Interactive Multiview Memory Network (DIMMN) model, which integrates interaction information and mines crossmodal dynamic dependencies for emotion recognition. Experimental results show that DIMMN achieves better performance compared to state-of-the-art methods.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Dazhi Jiang, Runguo Wei, Jintao Wen, Geng Tu, Erik Cambria
Summary: Emotion recognition in conversations has wide applications in various fields. We propose an AutoML strategy based on emotion congruent effect to select suitable knowledge and models, and effectively capture context information and enhance external knowledge in conversations.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Frank Xing, Bjoern Schuller, Iti Chaturvedi, Erik Cambria, Amir Hussain
Summary: Neural network-based methods, such as word2vec and GPT-based models, have achieved significant progress in AI research, especially in handling large datasets. However, these methods lack in-depth understanding of the internal features and representations of the data, leading to various problems and concerns.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Kai He, Rui Mao, Tieliang Gong, Chen Li, Erik Cambria
Summary: The study proposes a meta-based self-training method for aspect-based sentiment analysis (ABSA). By generating pseudo-labels and controlling convergence rates, the method improves model performance and accuracy in fine-grained sentiment analysis.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Geng Tu, Bin Liang, Dazhi Jiang, Ruifeng Xu
Summary: This article proposes a knowledge selection framework called SKSEC that incorporates sentiment emotion and context to improve emotion recognition in conversations. By eliminating and refining external knowledge, the performance of the model can be effectively enhanced.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Rui Mao, Qian Liu, Kai He, Wei Li, Erik Cambria
Summary: With the breakthrough of large-scale pre-trained language model (PLM) technology, prompt-based classification tasks, such as sentiment analysis and emotion detection, have gained increasing attention. This study conducts a systematic empirical study on prompt-based sentiment analysis and emotion detection to investigate the biases of PLMs in affective computing.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Tan Yue, Rui Mao, Heng Wang, Zonghai Hu, Erik Cambria
Summary: Sarcasm detection is a challenging task in natural language processing, especially in the context of social media where sarcasm is prevalent. This paper proposes a novel model called KnowleNet that incorporates prior knowledge and cross-modal semantic contrast for multimodal sarcasm detection. By leveraging the ConceptNet knowledge base and utilizing contrastive learning, the model achieves state-of-the-art performance on benchmark datasets.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jialun Wu, Kai He, Rui Mao, Chen Li, Erik Cambria
Summary: Predicting a patient's future health condition is a trending topic in the intelligent medical field. This paper proposes a knowledge-guided predictive framework called MEGACare, which leverages multi-faceted medical knowledge and multi-view learning to enhance clinical prediction accuracy.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Kai He, Rui Mao, Yucheng Huang, Tieliang Gong, Chen Li, Erik Cambria
Summary: In this paper, a prompt-based contrastive learning method is proposed for few-shot NER tasks. The method leverages external knowledge to initialize semantic anchors and optimizes prompts and sentence embeddings with a proposed semantic-enhanced contrastive loss. The method outperforms traditional contrastive learning methods in few-shot scenarios and effectively addresses the issues in conventional methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)