InPHYNet: Leveraging attention-based multitask recurrent networks for multi-label physics text classification

Udandarao, Vishaal; Agarwal, Abhishek; Gupta, Anubha; Chakraborty, Tanmoy

doi:10.1016/j.knosys.2020.106487

Cited by 7 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main goal of natural language processing in computer science is to create computational theories and empower systems to understand human language using machine learning algorithms and discover the relationships between documents [31]. MLTC is extensively used in a variety of applications such as document classification [32], web content classification [33,34], and recommendation systems [35,36]. MLTC is a complex task in NLP that requires the provisioning of multiple labels for a single instance.…”

Section: Mltcmentioning

confidence: 99%

A New Hybrid Based on Long Short-Term Memory Network with Spotted Hyena Optimization Algorithm for Multi-Label Text Classification

et al. 2022

View full text Add to dashboard Cite

An essential work in natural language processing is the Multi-Label Text Classification (MLTC). The purpose of the MLTC is to assign multiple labels to each document. Traditional text classification methods, such as machine learning usually involve data scattering and failure to discover relationships between data. With the development of deep learning algorithms, many authors have used deep learning in MLTC. In this paper, a novel model called Spotted Hyena Optimizer (SHO)-Long Short-Term Memory (SHO-LSTM) for MLTC based on LSTM network and SHO algorithm is proposed. In the LSTM network, the Skip-gram method is used to embed words into the vector space. The new model uses the SHO algorithm to optimize the initial weight of the LSTM network. Adjusting the weight matrix in LSTM is a major challenge. If the weight of the neurons to be accurate, then the accuracy of the output will be higher. The SHO algorithm is a population-based meta-heuristic algorithm that works based on the mass hunting behavior of spotted hyenas. In this algorithm, each solution of the problem is coded as a hyena. Then the hyenas are approached to the optimal answer by following the hyena of the leader. Four datasets are used (RCV1-v2, EUR-Lex, Reuters-21578, and Bookmarks) to evaluate the proposed model. The assessments demonstrate that the proposed model has a higher accuracy rate than LSTM, Genetic Algorithm-LSTM (GA-LSTM), Particle Swarm Optimization-LSTM (PSO-LSTM), Artificial Bee Colony-LSTM (ABC-LSTM), Harmony Algorithm Search-LSTM (HAS-LSTM), and Differential Evolution-LSTM (DE-LSTM). The improvement of SHO-LSTM model accuracy for four datasets compared to LSTM is 7.52%, 7.12%, 1.92%, and 4.90%, respectively.

show abstract

Section: Mltcmentioning

confidence: 99%

A New Hybrid Based on Long Short-Term Memory Network with Spotted Hyena Optimization Algorithm for Multi-Label Text Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The primary objective of NLP is to utilize mathematical models and algorithms to enable computers to better comprehend and rationalize associations inside and amongst documents [51]. MLTC is primarily used for document classification in several applications [52]. Additionally, MLTC is commonly utilized for the classification of web content [53,54] and recommendation systems to better comprehend context [55,56].…”

Section: Multi-label Text Classificationmentioning

confidence: 99%

“…The current literature review confirms the necessity for MLTC of news. A primary CNN is inefficient for MLTC tasks [52]. The performance of a CNN is extremely dependent on the tuning of its hyperparameters, and automation of hyperparameters is crucial work in the field of CNN optimization.…”

Section: Name Contributions Limitationsmentioning

confidence: 99%

SHO-CNN: A Metaheuristic Optimization of a Convolutional Neural Network for Multi-Label News Classification

Nadeem

Ahmed

et al. 2022

Electronics

View full text Add to dashboard Cite

News media always pursue informing the public at large. It is impossible to overestimate the significance of understanding the semantics of news coverage. Traditionally, a news text is assigned to a single category; however, a piece of news may contain information from more than one domain. A multi-label text classification model for news is proposed in this paper. The proposed model is an automated expert system designed to optimize CNN’s classification of multi-label news items. The performance of a CNN is highly dependent on its hyperparameters, and manually tweaking their values is a cumbersome and inefficient task. A high-level metaheuristic optimization algorithm, spotted hyena optimizer (SHO), has higher advanced exploration and exploitation capabilities. SHO generates a collection of solutions as a group of hyperparameters to be optimized, and the process is repeated until the desired optimal solution is achieved. SHO is integrated to automate the tuning of the hyperparameters of a CNN, including learning rate, momentum, number of epochs, batch size, dropout, number of nodes, and activation function. Four publicly available news datasets are used to evaluate the proposed model. The tuned hyperparameters and higher convergence rate of the proposed model result in higher performance for multi-label news classification compared to a baseline CNN and other optimizations of CNNs. The resulting accuracies are 93.6%, 90.8%, 68.7%, and 95.4% for RCV1-v2, Reuters-21578, Slashdot, and NELA-GT-2019, respectively.

show abstract

“…They used neural network analysis models to evaluate and classify question level, answer level, and feedback level, constructing a comprehensive, rapid, and accurate method for evaluating classroom dialogue [5]. Vishaal established a recursive interleaved multi-task learning network that can be used for any general multi-label classification task related to the field of education [6]. Compared with the traditional classification methods, which mainly use supervised methods, relying on existing natural language processing tools can easily lead to error accumulation problems in the processing process.…”

Section: Introductionmentioning

confidence: 99%

Design of an Automatic Classification System for Educational Reform Documents Based on Naive Bayes Algorithm

Zhang,

Ma,

Ren

et al. 2024

Mathematics

View full text Add to dashboard Cite

With the continuous deepening of educational reform, a large number of educational policies, programs, and research reports have emerged, bringing a heavy burden of information processing and management to educators. Traditional manual classification and archiving methods are inefficient and susceptible to subjective factors. Therefore, an automated method is needed to quickly and accurately classify and archive documents into their respective categories. Based on this, this paper proposes a design of an automatic document classification system for educational reform based on the Naive Bayes algorithm to address the challenges of document management in the education field. Firstly, the relevant literature and document data in the field of educational reform are collected and organized to establish an annotated dataset for model detection. Secondly, the raw data are preprocessed by cleaning and transforming the original text data to make them more suitable for input into machine learning algorithms. Thirdly, various algorithms are trained and selected to determine the best algorithm for classifying educational reform documents. Finally, based on the determined algorithm, a corresponding classification software is designed to automatically classify and archive educational reform documents for analysis. Through experimental evaluation and result analysis, this research demonstrates the effectiveness and accuracy of the education reform document automatic classification system based on the Naive Bayes algorithm. This method can efficiently classify a large number of documents into their respective categories quickly and accurately, thereby improving the efficiency of educators and their information management capabilities. In the future, further exploration of feature extraction methods and machine learning algorithms can be conducted to optimize the classification performance and apply this method to practical management and decision-making in the education field.

show abstract

InPHYNet: Leveraging attention-based multitask recurrent networks for multi-label physics text classification

Cited by 7 publications

References 24 publications

A New Hybrid Based on Long Short-Term Memory Network with Spotted Hyena Optimization Algorithm for Multi-Label Text Classification

A New Hybrid Based on Long Short-Term Memory Network with Spotted Hyena Optimization Algorithm for Multi-Label Text Classification

SHO-CNN: A Metaheuristic Optimization of a Convolutional Neural Network for Multi-Label News Classification

Design of an Automatic Classification System for Educational Reform Documents Based on Naive Bayes Algorithm

Contact Info

Product

Resources

About