Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00061
Carlin Chun-Fai Chu, Raymond So, Simon Siu-Wai Li, Ernest Kan-Lam Kwong, Chun-Hung Chiu
This study develops a new expert system framework to address the issue of early detection of cyberbullying incidents in Chinese-English code-mixed language on social media networks. The framework covers the crawling of session-based social media texts with potential cyberbullying messages with a crowdsourcing web application to systematically retrieve and manually annotate a cyberbullying dataset, and most importantly establishes an explainable artificial intelligence model based on natural language processing algorithm for identification of targeted emotional colloquial slang phrases and machine learning method using Shapley value and transfer learning approach for automatic early detection of cyberbullying incidents in Chinese-English codemixed language.
{"title":"A Framework for Early Detection of Cyberbullying in Chinese-English Code-Mixed Social Media Text Using Natural Language Processing and Machine Learning","authors":"Carlin Chun-Fai Chu, Raymond So, Simon Siu-Wai Li, Ernest Kan-Lam Kwong, Chun-Hung Chiu","doi":"10.1109/ICNLP58431.2023.00061","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00061","url":null,"abstract":"This study develops a new expert system framework to address the issue of early detection of cyberbullying incidents in Chinese-English code-mixed language on social media networks. The framework covers the crawling of session-based social media texts with potential cyberbullying messages with a crowdsourcing web application to systematically retrieve and manually annotate a cyberbullying dataset, and most importantly establishes an explainable artificial intelligence model based on natural language processing algorithm for identification of targeted emotional colloquial slang phrases and machine learning method using Shapley value and transfer learning approach for automatic early detection of cyberbullying incidents in Chinese-English codemixed language.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76823823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00018
Da Ai, Ce Xu, Xiaoyang Zhang, Yu Ai, Yansong Bai, Y. Liu
Point cloud semantic segmentation is widely used in scene analysis. We propose a point cloud semantic segmentation network based on adaptive random sampling and self-attention. The network extracts local centroids using random sampling, enriches feature information of the centroids using the proposed adaptive optimization module, and then learns correlations and differences between feature vectors using a feature aggregation module based on the self-attentiveness mechanism to make feature cross-fertilization more adequate, which effectively improves the performance of semantic segmentation. Experimental results on S3DIS show that the network consumes less computing time, but improves the Mean Intersection over Union (mIou) by 14.4% and overall accuracy (oAcc) by 6.4% over the baseline network PointNet++.
{"title":"ASSA-Net: Semantic Segmentation Network for Point Clouds Based on Adaptive Sampling and Self-Attention","authors":"Da Ai, Ce Xu, Xiaoyang Zhang, Yu Ai, Yansong Bai, Y. Liu","doi":"10.1109/ICNLP58431.2023.00018","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00018","url":null,"abstract":"Point cloud semantic segmentation is widely used in scene analysis. We propose a point cloud semantic segmentation network based on adaptive random sampling and self-attention. The network extracts local centroids using random sampling, enriches feature information of the centroids using the proposed adaptive optimization module, and then learns correlations and differences between feature vectors using a feature aggregation module based on the self-attentiveness mechanism to make feature cross-fertilization more adequate, which effectively improves the performance of semantic segmentation. Experimental results on S3DIS show that the network consumes less computing time, but improves the Mean Intersection over Union (mIou) by 14.4% and overall accuracy (oAcc) by 6.4% over the baseline network PointNet++.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84327513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00082
Yanwei Huo, Hongyu Cheng
PageRank algorithm in the calculation of nodes is equally distributed to the node chain of all nodes, but in the actual production of manufacturing enterprises, the importance of process knowledge in process documents is different, if according to the PageRank algorithm PR value equal transfer to calculate the importance of the artifact, efficiency and accuracy is generally low, so the importance of PR value transfer difference should be considered. Therefore, this paper introduces K-Shell decomposition algorithm in PageRank algorithm, constructs a new I-PageRank algorithm model, adding the importance of each node in the linked network to the PageRank algorithm, which improves the efficiency and accuracy of PageRank algorithm in identifying key nodes.
{"title":"Research on I-PageRank algorithm model of Process knowledge graph based on K-Shell decomposition algorithm","authors":"Yanwei Huo, Hongyu Cheng","doi":"10.1109/ICNLP58431.2023.00082","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00082","url":null,"abstract":"PageRank algorithm in the calculation of nodes is equally distributed to the node chain of all nodes, but in the actual production of manufacturing enterprises, the importance of process knowledge in process documents is different, if according to the PageRank algorithm PR value equal transfer to calculate the importance of the artifact, efficiency and accuracy is generally low, so the importance of PR value transfer difference should be considered. Therefore, this paper introduces K-Shell decomposition algorithm in PageRank algorithm, constructs a new I-PageRank algorithm model, adding the importance of each node in the linked network to the PageRank algorithm, which improves the efficiency and accuracy of PageRank algorithm in identifying key nodes.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89226952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/icnlp58431.2023.00077
Yani Qiao, Bo Li, Wen Cui, Yuji Li
This paper proposes a mode detection algorithm based on digital radio (DRM) system. DRM system is a digital broadcasting standard including long wave, medium wave and short wave, which is applicable to digital broadcasting below 30dB. By selecting different transmission modes, signals can be effectively transmitted in different channels and under different conditions. DRM system standard defines four different transmission modes (also known as robust mode). The main differences between these modes are the number of subcarriers, subcarrier spacing, pilot and other structures of OFDM symbols. Therefore, on the basis of completing the time synchronization corresponding to the four transmission modes, this paper proposes a mode detection algorithm based on synchronization analysis, which can effectively identify the transmission mode used by the transmission signal when obtaining the transmission signal, so as to better complete the follow-up signal processing work such as synchronization and channel estimation.
{"title":"Robust Mode Detection Based on DRM System","authors":"Yani Qiao, Bo Li, Wen Cui, Yuji Li","doi":"10.1109/icnlp58431.2023.00077","DOIUrl":"https://doi.org/10.1109/icnlp58431.2023.00077","url":null,"abstract":"This paper proposes a mode detection algorithm based on digital radio (DRM) system. DRM system is a digital broadcasting standard including long wave, medium wave and short wave, which is applicable to digital broadcasting below 30dB. By selecting different transmission modes, signals can be effectively transmitted in different channels and under different conditions. DRM system standard defines four different transmission modes (also known as robust mode). The main differences between these modes are the number of subcarriers, subcarrier spacing, pilot and other structures of OFDM symbols. Therefore, on the basis of completing the time synchronization corresponding to the four transmission modes, this paper proposes a mode detection algorithm based on synchronization analysis, which can effectively identify the transmission mode used by the transmission signal when obtaining the transmission signal, so as to better complete the follow-up signal processing work such as synchronization and channel estimation.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89516420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00062
Youyao Liu, Haimei Huang, Jialei Gao, Shihao Gai
Chinese Text Classification (TC) is the process of mapping text to a pre-given topics category. In recent years, it has been found that TC is mainly based on RNN and BERT, so the development of different novel pre-training applied to Chinese TC is described as based on BERT pre-training. BERT combined with convolutional neural network is proposed to extend the BERT-CNN model for the problem of lack of semantic knowledge of BERT to derive a good classification effect. The second RoBERTa model performs feature extraction and fusion to obtain the feature word vector as the text output vector, which can solve the problem of insufficient BERT extracted features. The BERT-BiGRU model, on the other hand, mainly avoids the increase in the number of texts leading to long training time and overfitting, and uses a simpler GRU bi-word network as the main network to fully extract the contextual information of Chinese texts and finally complete the classification of Chinese texts; at the same time, it makes an outlook and conclusion on the new pre-training model for Chinese TC.
{"title":"A study of Chinese Text Classification based on a new type of BERT pre-training","authors":"Youyao Liu, Haimei Huang, Jialei Gao, Shihao Gai","doi":"10.1109/ICNLP58431.2023.00062","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00062","url":null,"abstract":"Chinese Text Classification (TC) is the process of mapping text to a pre-given topics category. In recent years, it has been found that TC is mainly based on RNN and BERT, so the development of different novel pre-training applied to Chinese TC is described as based on BERT pre-training. BERT combined with convolutional neural network is proposed to extend the BERT-CNN model for the problem of lack of semantic knowledge of BERT to derive a good classification effect. The second RoBERTa model performs feature extraction and fusion to obtain the feature word vector as the text output vector, which can solve the problem of insufficient BERT extracted features. The BERT-BiGRU model, on the other hand, mainly avoids the increase in the number of texts leading to long training time and overfitting, and uses a simpler GRU bi-word network as the main network to fully extract the contextual information of Chinese texts and finally complete the classification of Chinese texts; at the same time, it makes an outlook and conclusion on the new pre-training model for Chinese TC.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82681100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00022
Shuying Li, Qiang Zhang, Lei Cheng, Baidong Peng
Since the excellent performance of Support Vector Machine (SVM) in handling with high-dimensional data, it is often used in the field of hyperspectral image (HSI) classification. However, traditional SVM methods only uses a single Mercer kernel function as base kernel, which does not represent the similarity of samples well. Meanwhile, it cannot utilize the spatial background information to enhance the HSI classification results. To address these issues, the paper proposes a two-stage learning (TSL) algorithm for HSI classification. In the first stage, a new Kernel Singular Value Decomposition-Multiple Kernel learning (KSVD-MKL) method is proposed for SVM Multiple Kernel Learning (MKL), which allows the best combination of kernels to be composed by using Gaussian kernels with different bandwidth scales. In the second stage, the KSVD-MKL classification is used as the initial spectral term classification results. Then, spatial information is modeled by using Conditional Random Field (CRF) observation fields and labels, and the KSVD-MKL classification results are optimized. Experiment results on public Indian pines and Botswana datasets demonstrate that the classification accuracy of the proposed method is effectively improved against existing algorithms.
由于支持向量机(SVM)在处理高维数据方面的优异性能，它经常被用于高光谱图像(HSI)分类领域。然而，传统的支持向量机方法仅使用单一的Mercer核函数作为基核，不能很好地代表样本的相似性。同时，无法利用空间背景信息增强HSI分类结果。为了解决这些问题，本文提出了一种用于HSI分类的两阶段学习(TSL)算法。首先，针对支持向量机多核学习(MKL)，提出了一种新的核奇异值分解-多核学习(KSVD-MKL)方法，利用不同带宽尺度的高斯核组成最佳的核组合;第二阶段使用KSVD-MKL分类作为初始光谱项分类结果。然后利用条件随机场(Conditional Random Field, CRF)观测场和标签对空间信息进行建模，并对KSVD-MKL分类结果进行优化。在印度松树和博茨瓦纳公共数据集上的实验结果表明，与现有算法相比，本文方法的分类精度得到了有效提高。
{"title":"A Two Stage Learning Algorithm for Hyperspectral Image Classification","authors":"Shuying Li, Qiang Zhang, Lei Cheng, Baidong Peng","doi":"10.1109/ICNLP58431.2023.00022","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00022","url":null,"abstract":"Since the excellent performance of Support Vector Machine (SVM) in handling with high-dimensional data, it is often used in the field of hyperspectral image (HSI) classification. However, traditional SVM methods only uses a single Mercer kernel function as base kernel, which does not represent the similarity of samples well. Meanwhile, it cannot utilize the spatial background information to enhance the HSI classification results. To address these issues, the paper proposes a two-stage learning (TSL) algorithm for HSI classification. In the first stage, a new Kernel Singular Value Decomposition-Multiple Kernel learning (KSVD-MKL) method is proposed for SVM Multiple Kernel Learning (MKL), which allows the best combination of kernels to be composed by using Gaussian kernels with different bandwidth scales. In the second stage, the KSVD-MKL classification is used as the initial spectral term classification results. Then, spatial information is modeled by using Conditional Random Field (CRF) observation fields and labels, and the KSVD-MKL classification results are optimized. Experiment results on public Indian pines and Botswana datasets demonstrate that the classification accuracy of the proposed method is effectively improved against existing algorithms.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73765973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/icnlp58431.2023.00020
Sai Ma, Haibo Ge, Wenhao He, Chaofeng Huang, Yu An, Ting Zhou
Human pose estimation is an important research direction in the field of computer vision. At present, the mainstream human pose estimation algorithms have high complexity, large amount of calculation, and cannot be run on resource-constrained devices such as mobile terminals, which severely limits the popularization and application of this technology. Aiming at the problem of increased network model parameters and computational complexity, based on the High-Resolution Network (HRNet), a lightweight human pose estimation network incorporating Ghost module and attention mechanism is proposed. Replaced with Ghost convolution, and added the attention mechanism Concurrent Spatial and Channel Squeeze and Channel Excitation Net module on this basis to ensure the prediction accuracy of the network. Under the same image resolution and environment configuration, the experimental results on the COCO dataset show that the improved network model reduces the number of parameters by 98.3% compared to the high-resolution network model, and reduces the computational complexity by 67.6%. The experimental results show that the improved network model can effectively reduce the amount of network parameters and reduce the computational complexity while maintaining a certain prediction accuracy.
{"title":"A Lightweight Human Pose Estimation Algorithm Based on High Resolution Network","authors":"Sai Ma, Haibo Ge, Wenhao He, Chaofeng Huang, Yu An, Ting Zhou","doi":"10.1109/icnlp58431.2023.00020","DOIUrl":"https://doi.org/10.1109/icnlp58431.2023.00020","url":null,"abstract":"Human pose estimation is an important research direction in the field of computer vision. At present, the mainstream human pose estimation algorithms have high complexity, large amount of calculation, and cannot be run on resource-constrained devices such as mobile terminals, which severely limits the popularization and application of this technology. Aiming at the problem of increased network model parameters and computational complexity, based on the High-Resolution Network (HRNet), a lightweight human pose estimation network incorporating Ghost module and attention mechanism is proposed. Replaced with Ghost convolution, and added the attention mechanism Concurrent Spatial and Channel Squeeze and Channel Excitation Net module on this basis to ensure the prediction accuracy of the network. Under the same image resolution and environment configuration, the experimental results on the COCO dataset show that the improved network model reduces the number of parameters by 98.3% compared to the high-resolution network model, and reduces the computational complexity by 67.6%. The experimental results show that the improved network model can effectively reduce the amount of network parameters and reduce the computational complexity while maintaining a certain prediction accuracy.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77942641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/icnlp58431.2023.00039
Youyao Liu, Jialei Gao, Haimei Huang, Yifan Liu
Semantic role labeling (SRL) is a technique to analyze the structure of predicates and thesis elements in a sentence as a unit. It plays an important role in Chinese information recognition processing. Among the models of SRL studied in recent years, most of them are based on bidirectional long and short term memory loop network and conditional random field. In this paper, we first narrate the SRL model based on BILSTM-CRF, based on which the second model narrates the SRL model integrating Bert and BILSTM-CRF models due to the ability of pre-training and fine-tuning of Bert model. However, since the word vectors in Chinese text are obtained based on word stitching in the context window, making the words between them influence each other, the word vectors depend on this joint relationship. Therefore, for this, Gate filtering mechanism is integrated to adjust it, and in the third model, Gate mechanism is added to filter and denoise the word vectors based on BILSTM-CRF to further improve the recognition ability of SRL.
{"title":"Chinese Semantic Role Labeling Based on BILSTM-CRF Extended Model","authors":"Youyao Liu, Jialei Gao, Haimei Huang, Yifan Liu","doi":"10.1109/icnlp58431.2023.00039","DOIUrl":"https://doi.org/10.1109/icnlp58431.2023.00039","url":null,"abstract":"Semantic role labeling (SRL) is a technique to analyze the structure of predicates and thesis elements in a sentence as a unit. It plays an important role in Chinese information recognition processing. Among the models of SRL studied in recent years, most of them are based on bidirectional long and short term memory loop network and conditional random field. In this paper, we first narrate the SRL model based on BILSTM-CRF, based on which the second model narrates the SRL model integrating Bert and BILSTM-CRF models due to the ability of pre-training and fine-tuning of Bert model. However, since the word vectors in Chinese text are obtained based on word stitching in the context window, making the words between them influence each other, the word vectors depend on this joint relationship. Therefore, for this, Gate filtering mechanism is integrated to adjust it, and in the third model, Gate mechanism is added to filter and denoise the word vectors based on BILSTM-CRF to further improve the recognition ability of SRL.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82945049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00081
Chenlin Xing, Tao Luo, Jie Lv, Zhilong Zhang
Knowledge graph is widely used in real life, but there is still a lot of missing information, which makes the completion of knowledge graph very important. Link prediction is one of the main methods to complete knowledge graph. In addition to binary relation facts which have received a lot of attention, there are also hyper-relation facts that are ubiquitous in the real world, namely n-ary relation facts. In this paper, we focus on link prediction algorithms for n-ary relation facts and find that the existing algorithms ignore the graph attribute information of nary relation facts themselves in the calculation process. Consequently, the distribution of entities and relations in n-ary relational datasets is analyzed first. The results show the fact that some of the n-ary relation facts are very important, while others are less important. This indicates that they have the characteristics of the scale-free network. Then, the global graph parameter (GGP) is introduced to describe the importance of entities and relations, and weighted to the link prediction process to improve the accuracy performance. Finally, extensive evaluation on commonly used n-ary datasets JF17K, WikiPeople, and their specific arity subsets validate the superiority of the proposed algorithm.
{"title":"N-ary Relational Link Prediction Algorithm Fusing Graph Attributes","authors":"Chenlin Xing, Tao Luo, Jie Lv, Zhilong Zhang","doi":"10.1109/ICNLP58431.2023.00081","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00081","url":null,"abstract":"Knowledge graph is widely used in real life, but there is still a lot of missing information, which makes the completion of knowledge graph very important. Link prediction is one of the main methods to complete knowledge graph. In addition to binary relation facts which have received a lot of attention, there are also hyper-relation facts that are ubiquitous in the real world, namely n-ary relation facts. In this paper, we focus on link prediction algorithms for n-ary relation facts and find that the existing algorithms ignore the graph attribute information of nary relation facts themselves in the calculation process. Consequently, the distribution of entities and relations in n-ary relational datasets is analyzed first. The results show the fact that some of the n-ary relation facts are very important, while others are less important. This indicates that they have the characteristics of the scale-free network. Then, the global graph parameter (GGP) is introduced to describe the importance of entities and relations, and weighted to the link prediction process to improve the accuracy performance. Finally, extensive evaluation on commonly used n-ary datasets JF17K, WikiPeople, and their specific arity subsets validate the superiority of the proposed algorithm.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86693892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-01DOI: 10.1109/ICNLP58431.2023.00059
Ratna Nirupama, Prakash Mondal
The present paper is a demonstration of the algorithm to integrate the representational principles of three grammar formalisms: constituency by Phrase Structure Grammar (PSG), head-dependency relations by Dependency Grammar (DG) and functor-argument relations by Categorial Grammar (CG) for achieving a unified representation. This algorithm is written for analyzing both continuous and discontinuous sentences in natural language and thereby provides a unique solution towards discontinuity in natural language. For mustrative purposes, a discontinuous relative clause from Salish has been taken to show the implementation of the algorithm. A discussion on the significance of this algorithm and the unified representation is present towards the end of the paper, followed by a conclusion.
{"title":"On the implementation of the algorithm for representation of discontinuity in natural language","authors":"Ratna Nirupama, Prakash Mondal","doi":"10.1109/ICNLP58431.2023.00059","DOIUrl":"https://doi.org/10.1109/ICNLP58431.2023.00059","url":null,"abstract":"The present paper is a demonstration of the algorithm to integrate the representational principles of three grammar formalisms: constituency by Phrase Structure Grammar (PSG), head-dependency relations by Dependency Grammar (DG) and functor-argument relations by Categorial Grammar (CG) for achieving a unified representation. This algorithm is written for analyzing both continuous and discontinuous sentences in natural language and thereby provides a unique solution towards discontinuity in natural language. For mustrative purposes, a discontinuous relative clause from Salish has been taken to show the implementation of the algorithm. A discussion on the significance of this algorithm and the unified representation is present towards the end of the paper, followed by a conclusion.","PeriodicalId":53637,"journal":{"name":"Icon","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89328728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：