ACM Transactions on Asian and Low-Resource Language Information Processing最新文献

{"title":"Fast Recurrent Neural Network with Bi-LSTM for Handwritten Tamil text segmentation in NLP","authors":"C. Vinotheni, Lakshmana Pandian S.","doi":"10.1145/3643808","DOIUrl":"https://doi.org/10.1145/3643808","url":null,"abstract":"<p>Tamil text segmentation is a long-standing test in language comprehension that entails separating a record into adjacent pieces based on its semantic design. Each segment is important in its own way. The segments are organised according to the purpose of the content examination as text groups, sentences, phrases, words, characters or any other data unit. That process has been portioned using rapid tangled neural organisation in this research, which presents content segmentation methods based on deep learning in natural language processing (NLP). This study proposes a bidirectional long short-term memory (Bi-LSTM) neural network prototype in which fast recurrent neural network (FRNN) are used to learn Tamil text group embedding and phrases are fragmented using text-oriented data. As a result, this prototype is capable of handling variable measured setting data and gives a vast new dataset for naturally segmenting text in Tamil. In addition, we develop a segmentation prototype and show how well it sums up to unnoticeable regular content using this dataset as a base. With Bi-LSTM, the segmentation precision of FRNN is superior to that of other segmentation approaches; however, it is still inferior to that of certain other techniques. Every content is scaled to the required size in the proposed framework, which is immediately accessible for the preparation. This means, each word in a scaled Tamil text is employed to prepare neural organisation as fragmented content. The results reveal that the proposed framework produces high rates of segmentation for manually authored material that are nearly equivalent to segmentation-based plans.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"16 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139752555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media via Multi-label Prediction and Determinantal Point Processes","authors":"Jie Liu, Yaguang Li, Shizhu He, Shun Wu, Kang Liu, Shenping Liu, Jiong Wang, Qing Zhang","doi":"10.1145/3644074","DOIUrl":"https://doi.org/10.1145/3644074","url":null,"abstract":"<p>Social media produces large amounts of contents every day. How to predict the potential influences of the contents from a social reply feedback perspective is a key issue that has not been explored. Thus, we propose a novel task named reply keyword prediction in social media, which aims to predict the keywords in the potential replies as many aspects as possible. One prerequisite challenge is that the accessible social media datasets labeling such keywords remain absent. To solve this issue, we propose a new dataset, to study the reply keyword prediction in Social Media. This task could be seen as a single-turn dialogue keyword prediction for open-domain dialogue system. However, existing methods for dialogue keyword prediction cannot be adopted directly, which have two main drawbacks. First, they do not provide an explicit mechanism to model topic complementarity between keywords which is crucial in social media to controllably model all aspects of replies. Second, the collocations of keywords are not explicitly modeled, which also makes it less controllable to optimize for fine-grained prediction since the context information is much less than that in dialogue. To address these issues, we propose a two-stage disentangled framework, which can optimize the complementarity and collocation explicitly in a disentangled fashion. In the first stage, we use a sequence-to-set paradigm via multi-label prediction and determinantal point processes, to generate a set of keyword seeds satisfying the complementarity. In the second stage, we adopt a set-to-sequence paradigm via seq2seq model with the keyword seeds guidance from the set, to generate the more-fine-grained keywords with collocation. Experiments show that this method can generate not only a more diverse set of keywords but also more relevant and consistent keywords. Furthermore, the keywords obtained based on this method can achieve better reply generation results in the retrieval-based system than others.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"1 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139752535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved BIO-based Chinese Automatic Abstract-generation Model","authors":"Qing Li, Weibin Wan, Yuming Zhao, Xiaoyan Jiang","doi":"10.1145/3643695","DOIUrl":"https://doi.org/10.1145/3643695","url":null,"abstract":"<p>With its unique information-filtering function, text summarization technology has become a significant aspect of search engines and question-and-answer systems. However, existing models that include the copy mechanism often lack the ability to extract important fragments, resulting in generated content that suffers from thematic deviation and insufficient generalization. Specifically, Chinese automatic summarization using traditional generation methods often loses semantics because of its reliance on word lists. To address these issues, we proposed the novel BioCopy mechanism for the summarization task. By training the tags of predictive words and reducing the probability distribution range on the glossary, we enhanced the ability to generate continuous segments, which effectively solves the above problems. Additionally, we applied reinforced canonicality to the inputs to obtain better model results, making the model share the sub-network weight parameters and sparsing the model output to reduce the search space for model prediction. To further improve the model’s performance, we calculated the bilingual evaluation understudy (BLEU) score on the English dataset CNN/DailyMail to filter the thresholds and reduce the difficulty of word separation and the dependence of the output on the word list. We fully fine-tuned the model using the LCSTS dataset for the Chinese summarization task and conducted small-sample experiments using the CSL dataset. We also conducted ablation experiments on the Chinese dataset. The experimental results demonstrate that the optimized model can learn the semantic representation of the original text better than other models and performs well with small sample sizes.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"304 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139752620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Expert System for Indian Sign Language Recognition using Spatial Attention based Feature and Temporal Feature","authors":"Soumen Das, Saroj Kr. Biswas, Biswajit Purkayastha","doi":"10.1145/3643824","DOIUrl":"https://doi.org/10.1145/3643824","url":null,"abstract":"<p>Sign Language (SL) is the only means of communication for the hearing-impaired people. Normal people have difficulty understanding SL, resulting in a communication barrier between hearing impaired people and hearing community. However, the Sign Language Recognition System (SLRS) has helped to bridge the communication gap. Many SLRs are proposed for recognizing SL; however, a limited number of works are reported for Indian Sign Language (ISL). Most of the existing SLRS focus on global features other than the Region of Interest (ROI). Focusing more on the hand region and extracting local features from the ROI improves system accuracy. The attention mechanism is a widely used technique for emphasizing the ROI. However, only a few SLRS used the attention method. They employed the Convolution Block Attention Module (CBAM) and temporal attention but Spatial Attention (SA) is not utilized in previous SLRS. Therefore, a novel SA based SLRS named Spatial Attention-based Sign Language Recognition Module (SASLRM) is proposed to recognize ISL words for emergency situations. SASLRM recognizes ISL words by combining convolution features from a pretrained VGG-19 model and attention features from a SA module. The proposed model accomplished an average accuracy of 95.627% on the ISL dataset. The proposed SASLRM is further validated on LSA64, WLASL and Cambridge Hand Gesture Recognition (HGR) datasets where, the proposed model reached an accuracy of 97.84 %, 98.86% and 98.22’% respectively. The results indicate the effectiveness of the proposed SLRS in comparison with the existing SLRS.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"13 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139678930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Construction of Interval-Valued Fuzzy Hindi WordNet using Lexico-Syntactic Patterns and Word Embeddings","authors":"Minni Jain, Rajni Jindal, Amita Jain","doi":"10.1145/3643132","DOIUrl":"https://doi.org/10.1145/3643132","url":null,"abstract":"<p>A computational lexicon is the backbone of any language processing system. It helps computers to understand the language complexity as a human does by inculcating words and their semantic associations. Manually constructed famous Hindi WordNet (HWN) consists of various classical semantic relations (crisp relations). To handle uncertainty and represent Hindi WordNet more semantically, Type- 1 fuzzy graphs are applied to relations of Hindi WordNet. But uncertainty in the crisp membership degree is not considered in Type 1 fuzzy set (T1FS). Also collecting billions (5,55,69,51,753 relations in HWN) of membership values from experts (humans) is not feasible. This paper applied the concept of Interval-Valued Fuzzy graphs and proposed Interval- Valued Fuzzy Hindi WordNet (IVFHWN). IVFHWN automatically identifies Interval- Valued Fuzzy relations between words and their degree of membership using word embeddings and lexico-syntactic patterns. The experimental results for the word sense disambiguation problem show better outcomes when IVFHWN is being used in place of Type 1 Fuzzy Hindi WordNet and classical Hindi WordNet.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"42 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139667272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi View Image Fusion Using Ensemble Deep Learning Algorithm for Mri and CT Images","authors":"N. Thenmoezhi, B. Perumal, A. Lakshmi","doi":"10.1145/3640811","DOIUrl":"https://doi.org/10.1145/3640811","url":null,"abstract":"<p>Medical image fusions are crucial elements in image based health care diagnostics or therapies, and generically applications of computer visions. However, majority of existing methods suffer from noise distortion that affect the overall output. When pictures are distorted by noises, classical fusion techniques perform badly. Hence, fusion techniques that properly maintain information comprehensively from multiple faulty pictures need to be created. This work presents ESLOs (Enhanced Lion Swarm Optimizations) with EDL (Ensemble Deep Learning) to address the aforementioned issues. The primary steps in this study include image fusions, segmentation, noise reduction, feature extraction, picture classification, and feature selection.AMFs (Adaptive Median Filters) are first used for noise removal in sequence to enhance image quality by eliminating noises. The MRIs and CTS images are then segmented using the RKMC algorithm to separate the images into their component regions or objects. Images in black and white are divided into image. In the white image, the RKMC algorithm successfully considered the earlier tumour probability. The next step is feature extraction, which is accomplished by using the MPCA (Modified Principal Component Analysis) to draw out the most informative aspects of the images. Then, ELSOs algorithm is applied for optimal feature selection which is computed by best fitness values. After that, multi view image fusions of multi modal images derive lower, middle and higher level images contents. It is done by using DCNNs (Deep Convolution Neural Networks) and TAcGANs (Tissue-Aware conditional Generative Adversarial Networks) algorithm which fuses the multi view features and relevant image features and it is used for real time applications. The results of this study implies that proposed ELSO+EDL algorithm results in better performances in terms of higher values of accuracies, PSNR and lower RMSE, MAPE with faster executions when compared to other existing algorithms.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"283 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139646778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Understanding the performance of AI algorithms in Text-Based Emotion Detection for Conversational Agents","authors":"Sheetal D. Kusal, Shruti G. Patil, Jyoti Choudrie, Ketan V. Kotecha","doi":"10.1145/3643133","DOIUrl":"https://doi.org/10.1145/3643133","url":null,"abstract":"<p>Current industry trends demand automation in every aspect, where machines could replace humans. Recent advancements in conversational agents have grabbed a lot of attention from industries, markets, and businesses. Building conversational agents that exhibit human communication characteristics is a need in today's marketplace. Thus, by accumulating emotions, we can build emotionally-aware conversational agents. Emotion detection in text-based dialogues has turned into a pivotal component of conversational agents, enhancing their ability to understand and respond to users' emotional states. This paper extensively compares various AI - techniques adapted to text-based emotion detection for conversational agents. This study covers a wide range of methods ranging from machine learning models to cutting-edge pre-trained models as well as deep learning models. The authors evaluate the performance of these techniques on the benchmark unbalanced topical chat and empathetic dialogue, balanced datasets. This paper offers an overview of the practical implications of emotion detection techniques in conversational systems and their impact on user response. The outcomes of this paper contribute to the ongoing development of empathetic conversational agents, emphasizing natural human-machine interactions.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"27 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139646764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Human Emotion Recognition Based on Machine Learning Algorithms with low Resource Environment","authors":"Asha P., Hemamalini V., Poongodaia., Swapna N., Soujanya K. L. S., Vaishali Gaikwad (Mohite)","doi":"10.1145/3640340","DOIUrl":"https://doi.org/10.1145/3640340","url":null,"abstract":"<p>It is difficult to discover significant audio elements and conduct systematic comparison analyses when trying to automatically detect emotions in speech. In situations when it is desirable to reduce memory and processing constraints, this research deals with emotion recognition. One way to achieve this is by reducing the amount of features. In this study, propose \"Active Feature Selection\" (AFS) method and compares it against different state-of-the-art techniques. According to the results, smaller subsets of features than the complete feature set can produce accuracy that is comparable to or better than the full feature set. The memory and processing requirements of an emotion identification system will be reduced, which can minimise the hurdles to using health monitoring technology. The results show by using 696 characteristics, the AFS technique for emobase yields a Unweighted average recall (UAR) of 75.8%.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"64 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139580337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fuzzified Deep Learning based Forgery Detection of Signatures in the Healthcare Mission Records","authors":"Ishu Priya, Nisha Chaurasia, Ashutosh Kumar Singh, Nakul Mehta, Abhishek Singh Kilak, Ahmed Alkhayyat","doi":"10.1145/3641818","DOIUrl":"https://doi.org/10.1145/3641818","url":null,"abstract":"<p>In an era subjected to digital solutions, handwritten signatures continue playing a crucial role in identity verification and document authentication. These signatures, a form of bio-metric verification, are unique to every individual, serving as a primitive method for confirming identity and ensuring security of an individual. Signatures, apart from being a means of personal authentication, are often considered a cornerstone in the validation of critical documents and processes, especially within the healthcare sector. In healthcare missions, particularly in the regions that are underdeveloped, hand-written records persist as the primary mode of documentation. The credibility of these handwritten documents hinges on the authenticity of the accompanying signatures, making signature verification a paramount safeguard for the integrity and security of medical information. Nonetheless, traditional offline methods of signature identification can be time-consuming and inefficient, particularly while dealing with a massive volume of documents. This arises the evident need for automated signature verification systems. Our research introduces an innovative signature verification system which synthesizes the strengths of fuzzy logic and CNN (Convolutional Neural Networks) to deliver precise and efficient signature verification. Leveraging the capabilities of Fuzzy Logic for feature representation and CNNs for discriminative learning, our proposed hybrid model offers a compelling solution. Through rigorous training, spanning a mere 28 epochs, our hybrid model exhibits remarkable performance by attaining a training accuracy of 91.29% and a test accuracy of 88.47%, underscoring its robust generalization capacity. In an era of evolving security requirements and the persistent relevance of handwritten signatures, our research links the disparity between tradition and modernity.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"39 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139554871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MODELLING A NOVEL APPROACH FOR EMOTION RECOGNITION USING LEARNING AND NATURAL LANGUAGE PROCESSING","authors":"Lakshmi Lalitha V., Dinesh Kumar Anguraj","doi":"10.1145/3641851","DOIUrl":"https://doi.org/10.1145/3641851","url":null,"abstract":"<p>Various facts, including politics, entertainment, industry, and research fields, are connected to analysing the audience's emotional. Syntactic Analysis (SA) is a Natural Language Processing (NLP) concept that uses statistical and lexical forms as well as learning techniques to forecast how different types of content in social media will express the audience's neutral, positive, and negative emotions. The lack of an adequate tool to quantify the characteristics and independent text for assessing the primary audience emotion from the available online social media dataset. The focus of this research is on modeling a cutting-edge method for decoding the connectivity among social media texts and assessing audience emotions. Here, a novel dense layer graph model (DLG-TF) for textual feature analysis is used to analyze the relevant connectedness inside the complex media environment to forecast emotions. The information from the social media dataset is extracted using some popular convolution network models, and the predictions are made by examining the textual properties. The experimental results show that, when compared to different standard emotions, the proposed DLG-TF model accurately predicts a greater number of possible emotions. The macro-average of baseline is 58%, the affective is 55%, the crawl is 55% and the ultra-dense is 59% respectively. The feature analysis comparison of baseline, affective, crawl, ultra-dense and DLG-TF using the unsupervised model based on EmoTweet gives the precision, recall and F1-score of the anticipated model are explained. The micro and macro average based on these parameters are compared and analyzed. The macro-average of baseline is 47%, the affective is 46%, the crawl is 50% and the ultra-dense is 85% respectively. It makes precise predictions using the social media dataset that is readily available. A few criteria, including accuracy, recall, precision, and F-measure, are assessed and contrasted with alternative methods.</p>","PeriodicalId":54312,"journal":{"name":"ACM Transactions on Asian and Low-Resource Language Information Processing","volume":"3 1","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139554971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}