Natural language processing based advanced method of unnecessary video detection

Moon, Nazmun Nessa; Salehin, Imrus; Parvin, Masuma; Hasan, Md. Mehedi; Talha, Iftakhar Mohammad; Debnath, Susanta Chandra; Nur, Fernaz Narin; Saifuzzaman, Mohd.

doi:10.11591/ijece.v11i6.pp5411-5419

Cited by 11 publications

(3 citation statements)

References 22 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applying appropriate evaluation metrics can optimize the active learning process by focusing on challenging samples that directly impact the overall quality of the image-to-LaTeX conversion. Domain adaptation techniques can also be utilized to improve the efficiency of active learning in OCR [63]. Due to domain differences, OCR models trained on synthetic data might struggle to perform well on real-world documents.…”

Section: Incorporating Active Learning Strategies For Ocr Model Impro...mentioning

confidence: 99%

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Orji,

Haydar,

Erşan

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

This paper comprehensively assesses the application of active learning strategies to enhance natural language processing-based optical character recognition (OCR) models for image-to-LaTeX conversion. It addresses the existing limitations of OCR models and proposes innovative practices to strengthen their accuracy. Key components of this study include the augmentation of training data with LaTeX syntax constraints, the integration of active learning strategies, and the employment of active learning feedback loops. This paper first examines the current weaknesses of OCR models with a particular focus on symbol recognition, complex equation handling, and noise moderation. These limitations serve as a framework against which the subsequent research methodologies are assessed. Augmenting the training data with LaTeX syntax constraints is a crucial strategy for improving model precision. Incorporating symbol relationships, wherein contextual information is considered during recognition, further enriches the error correction. This paper critically examines the application of active learning strategies. The active learning feedback loop leads to progressive improvements in accuracy. This article underlines the importance of uncertainty and diversity sampling in sample selection, ensuring that the dynamic learning process remains efficient and effective. Appropriate evaluation metrics and ensemble techniques are used to improve the operational learning effectiveness of the OCR model. These techniques allow the model to adapt and perform more effectively in diverse application domains, further extending its utility.

show abstract

Section: Incorporating Active Learning Strategies For Ocr Model Impro...mentioning

confidence: 99%

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Orji,

Haydar,

Erşan

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Removal of stop-words abridge the total bytes of the documents, therefore speedup the processing time of most information retrieval (IR) applications such as automatic text summarization, questions answering and recommendation system. It is described as a way of improving the performance of information retrieval in general [5]- [7] and such removal better the performance of some applications like search engines [8], text classification [9], detection of keyphrases [10], automatic detection of grammatical errors [11], computation of semantic similarity [12], identification sequence patterns [13], spam detection in e-mail [14], detection and removing unwanted videos [15], detection of hate speech [16], identification of named entity [17]. Non removal of stop words affects the process of automatic selecting keywords or important phrases from a document [18], [19].…”

Section: Introductionmentioning

confidence: 99%

Automatic construction of generic stop words list for hausa text

Bichi

Samsudin

Hassan

2022

IJEECS

View full text Add to dashboard Cite

Stop-words are words having the highest frequencies in a document without any significant information. They are characterized by having common relations within a cluster. They are the noise of the text that are evenly distributed over a document. Removal of stop words improve the performance and accuracy of information retrieval algorithms and machine learning at large. It saves the storage space by reducing the vector space dimension, and helps in effective documents indexing. This research generated a list of Hausa stop words automatically using aggregated method by combining frequency and statistics methods. The experiments are conducted using a primarily collected Hausa corpus consisting of 841 Hausa news articles of size 646862 words and finally a list of distinct 81 Hausa stop words is generated.

show abstract

“…The most noticeable and rapidly growing spheres in the context of videos are Daily motion and YouTube. YouTube is known as the largest repository of videos and is widely used for video sharing by billions of users [1]- [4]. However, given the massive number of videos on the web, users face difficulties in accurately retrieving and obtaining the videos they need [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Enhancing multi-class web video categorization model using machine and deep learning approaches

Yafooz

Alsaeedi

Alluhaibi

et al. 2022

IJECE

View full text Add to dashboard Cite

With today’s digital revolution, many people communicate and collaborate in cyberspace. Users rely on social media platforms, such as Facebook, YouTube and Twitter, all of which exert a considerable impact on human lives. In particular, watching videos has become more preferable than simply browsing the internet because of many reasons. However, difficulties arise when searching for specific videos accurately in the same domains, such as entertainment, politics, education, video and TV shows. This problem can be solved through web video categorization (WVC) approaches that utilize video textual information, visual features, or audio approaches. However, retrieving or obtaining videos with similar content with high accuracy is challenging. Therefore, this paper proposes a novel mode for enhancing WVC that is based on user comments and weighted features from video descriptions. Specifically, this model uses supervised learning, along with machine learning classifiers (MLCs) and deep learning (DL) models. Two experiments are conducted on the proposed balanced dataset on the basis of the two proposed algorithms based on multi-classes, namely, education, politics, health and sports. The model achieves high accuracy rates of 97% and 99% by using MLCs and DL models that are based on artificial neural network (ANN) and long short-term memory (LSTM), respectively.

show abstract

Natural language processing based advanced method of unnecessary video detection

Cited by 11 publications

References 22 publications

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Automatic construction of generic stop words list for hausa text

Enhancing multi-class web video categorization model using machine and deep learning approaches

Contact Info

Product

Resources

About