Arabic Natural Language Processing and Machine Learning-Based Systems

Marie-Sainte, Souad Larabi; Alalyani, Nada; Alotaibi, Sihaam; Ghouzali, Sanaa; Abunadi, Ibrahim

doi:10.1109/access.2018.2890076

Cited by 64 publications

(50 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, we plan to reimplement the Matlab source codes with C++ on our service robot platform. Except for object category recognition, the proposed methods can also be used in other fields with inadequate training data, such as brain-computer interface [34]- [36], natural language processing [37], [38] and remote sensing [39], [40] etc. Hence, using the proposed methods in other scientific research fields is also a meaningful work.…”

Section: Discussionmentioning

confidence: 99%

Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition

Yan

Zhuang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

When the training data is inadequate, it is difficult to train a deep Convolutional Neural Network (CNN) from scratch with randomized initial weights. Instead, it is common to train a source CNN model on a very large data set beforehand, and then use the learned source CNN model as an initialization to train a target CNN model. In deep learning realm, this procedure is called fine-tuning a CNN. This paper presents an experimental study on how to combine a collection of incrementally fine-tuned CNN models for crossdomain and multi-class object category recognition tasks. A group of fine-tuned CNN models is trained on the target data set by incrementally transferring parameters from a source CNN model trained on a large data set initially. The last two fully-connected (FC) layers of the source CNN model are eliminated, and two New FC layers are added to make the learned new CNN model suitable for the target task. Based on Caltech-101 and Office data sets, the experimental results demonstrate the effectiveness and good performance of the proposed methods. The proposed method is more suitable for the object recognition task when there is inadequate target training data. INDEX TERMS Convolutional neural network, object category recognition, ensemble learning, transfer learning.

show abstract

Section: Discussionmentioning

confidence: 99%

Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition

Yan

Zhuang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In other words, standard normalization systems of document length have traditionally ignored the issue of language peculiarities which has negative impacts on the validity and thus reliability of such methods. In natural language processing (NLP) of Arabic, the specific linguistic properties play a significant role in the success of NLP applications [5][6][7][8]. It is essential for NLP systems thus to consider the peculiarities of Arabic for more reliable results.…”

Section: Statement Of the Problemmentioning

confidence: 99%

Document Length Variation in the Vector Space Clustering of News in Arabic: A Comparison of Methods

Omar¹,

Hamouda²

2020

IJACSA

View full text Add to dashboard Cite

This article is concerned with addressing the effect of document length variation on measuring the semantic similarity in the text clustering of news in Arabic. Despite the development of different approaches for addressing the issue, there is no one strong conclusion recommending one approach. Furthermore, many of these have not been tested for the clustering of news in Arabic. The problem is that different length normalization methods can yield different analyses of the same data set, and that there is no obvious way of selecting the best one. The choice of an inappropriate method, however, has negative impacts on the accuracy and thus the reliability of clustering performance. Given the lack of agreement and disparity of opinions, we set out to comprehensively evaluate the existing normalization techniques to prove empirically which one is the best for the normalization of text length to improve the text clustering performance of news in Arabic. For this purpose, a corpus of 693 stories representing different categories and of different lengths is designed. Data is analyzed using different document length normalization methods along with vector space clustering (VSC), and then the analysis on which the clustering structure agrees most closely with the bibliographic information of the news stories is selected. The analysis of the data indicates that the clustering structure based on the byte length normalization method is the most accurate one. One main problem, however, with this method is that the lexical variables within the data set are not ranked which makes it difficult for retaining only the most distinctive lexical features for generating clustering structures based on semantic similarity. As thus, the study proposes the integration of TF-IDF for ranking the words within all the documents so that only those with the highest TF-IDF values are retained. It can be finally concluded that the proposed model proved effective in improving the function of the byte normalization method and thus on the performance and reliability of news clustering in Arabic. The findings of the study can also be extended to IR applications in Arabic. The proposed model can be usefully used in supporting the performance of the retrieval systems of Arabic in finding the most relevant documents for a given query based on semantic similarity, not document length.

show abstract

“…Recently, there have been many attempts to incorporate attention processing to improve algorithm performance in various tasks. Marie-Sainte et al [9] propose to combine global attention and local attention for neural machine translation. Stollenga et al [19] introduce a deep attention selective network to solve image classification task.…”

Section: Related Work a Attention Mechanismmentioning

confidence: 99%

“…Followed by the success of the attention model used in natural language processing [9] and image caption generation [10], many researchers apply the attention mechanism to action recognition tasks. For example, the movements of the hand at the table tennis matches are more useful than other body parts and we should pay more attention to the upper limbs.…”

Section: Introductionmentioning

confidence: 99%

An Improved Attention-Based Spatiotemporal-Stream Model for Action Recognition in Videos

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Action recognition is an important yet challenging task in computer vision. Attention mechanism not only tells where to focus but when to focus. It plays a key role in extracting discriminative spatial and temporal features for solving the task. In this paper, we propose an improved spatiotemporal attention model based on the two-stream structure to recognize the different actions in videos. Specifically, we first extract the intra-frame spatial features and inter-frame optical flow features for each video data. Then we implement an effective attention module, which sequentially infers attention maps along three separate dimensions: channel, spatial and temporal. After adaptive feature refinement based on the attention maps, we perform a temporal pooling process to squeeze the temporal dimension. Then, these achieved spatial and temporal features are fed into the spatial LSTM and temporal LSTM, respectively. Finally, we fuse the spatial feature, temporal feature and two-stream fusion feature to classify the actions in videos. Additionally, we also collect and construct a new Ping-Pong action dataset for subsequent human-robot interaction task from YouTube. It contains 2400 labeled videos for 4 categories. We compare with other action recognition algorithms and validate the feasibility and effectiveness of the proposed method on Ping-Pong action dataset and HMDB51 dataset.

show abstract

Arabic Natural Language Processing and Machine Learning-Based Systems

Cited by 64 publications

References 41 publications

Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition

Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition

Document Length Variation in the Vector Space Clustering of News in Arabic: A Comparison of Methods

An Improved Attention-Based Spatiotemporal-Stream Model for Action Recognition in Videos

Contact Info

Product

Resources

About