Unsupervised neural networks for automatic Arabic text summarization using document clustering and topic modeling

Alami, Nabil; Meknassi, Mohammed; En-Nahnahi, Noureddine; Adlouni, Yassine El; Ammor, Ouafae

doi:10.1016/j.eswa.2021.114652

Cited by 45 publications

(23 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted experiments on environmental pollution data, including a total of 4,000 samples, and the training set and the test set are divided according to the ratio of 5 : 1. e types of environmental pollution mainly include air pollution, air pollution, water pollution, soil pollution, and solid waste pollution. Each sample is a description of pretrial review and the corresponding draft Trm (L) Trm (L) Trm (L) Trm (3) Trm (3) Trm (3) Trm (3) Trm (2) Trm (2) Trm (2) Trm (2) Trm (1) Trm (1) Trm (1) Trm ( 1) 6 Mathematical Problems in Engineering recommendations for prosecution is considered as extractive summarization (reference summary). And the reference summaries are annotated by PhD in law from the University of Political Science and Law.…”

Section: Dataset and Data Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Sun

Yang

Wang

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The automatic generation of the draft procuratorial suggestions is to extract the description of illegal facts, administrative omission, description of laws and regulations, and other information from the case documents. Previously, the existing deep learning methods mainly focus on context-free word embeddings when addressing legal domain-speciﬁc extractive summarization tasks, which cannot get a better semantic understanding of the text and in turn leads to an adverse summarization performance. To this end, we propose a novel deep contextualized embeddings-based method BERTSLCA to conduct the extractive summarization task. The model is mainly based on the variant of BERT called BERTSUM. Firstly, the input document is fed into BERTSUM to get sentence-level embeddings. Then, we design an extracting architecture to catch the long dependency between sentences utilizing the Bi-Long Short-Term Memory (Bi-LSTM) unit, and at the end of the architecture, three cascaded convolution kernels with different sizes are designed to extract the relationships between adjacent sentences. Last, we introduce an attention mechanism to strengthen the ability to distinguish the importance of different sentences. To the best of our knowledge, this is the first work to use the pretrained language model for extractive summarization tasks in the field of Chinese judicial litigation. Experimental results on public interest litigation data and CAIL 2020 dataset all demonstrate that the proposed method achieves competitive performance.

show abstract

Section: Dataset and Data Preprocessingmentioning

confidence: 99%

“…Case investigators need to summarize some summary characteristics of the text from the complex case to form a procuratorial suggestion document. In such a background, the technique of automatic text summarization has attracted more and more attention from researchers [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Sun

Yang

Wang

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…In order to build effective model documents representation Nabil Alami et al [19] have submitted an approach using clustering, topic modelling, and unattended neural networks. First, on a large text collection, a document grouping technique using an Extreme learning machine was performed.…”

Section: Literature Reviewmentioning

confidence: 99%

Type2 IFC with SOA for Topic Detection and Document Clustering Analysis

Perumal¹,

Mathivanan²

2021

Preprint

View full text Add to dashboard Cite

The automatic document clustering and topic extraction from the corpus provides a very essential requirement in many real time applications. The document clustering and topic detection is utilized to locating data quickly. Hence, in this paper, Type 2 Intuitionistic Fuzzy Clustering and Seagull Optimization Algorithm (Type 2 IFCSOA) is developed for document clustering and topic detection. The Type 2 IFCSOA is utilized to cluster the documents. Additionally, ensemble approach is utilized to identify by the topics from the clustered documents. In the proposed methodology, the pre-processing is utilized to remove unwanted information from the documents such as tokenization, stop word removal and stemming process. After that, the proposed method is utilized to cluster the documents. The clustered documents are labeled with the basis of clusters. After that, to achieve topic detection, the ensemble approach is utilized with feature extraction phases such as Term Frequency- Inverse Document Frequency (TF-IDF), Mutual information (MI), Text Rank Algorithm and analysis of keyword taking out from co-occurrence statistical -Information (CSI). The proposed methodology is implemented in MATLAB and performances were evaluated with the statistical measurements such as precision, recall, accuracy, sensitivity, purity measure and entropy. The proposed method is compared with the conventional methods such as Fuzzy C Means clustering (FCM), FCM-Particle Swarm Optimization (PSO), FCM-Genetic Algorithm (GA) and K means clustering.

show abstract

“…Next, its inherent capacity to model various features that capture the features of sentiment in text. [14] trying to address this limitation by suggesting a novel method with topic modelling, unsupervised neural networks, and documents clustering for building effective document representations. Initially, a novel document clustering method with the Extreme learning machine (ELM) method is implemented on massive text collection.…”

Section: Introductionmentioning

confidence: 99%

Automated Multi-Document Biomedical Text Summarization Using Deep Learning Model

Almasoud¹,

Hassine²,

Al‐Wesabi³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Due to the advanced developments of the Internet and information technologies, a massive quantity of electronic data in the biomedical sector has been exponentially increased. To handle the huge amount of biomedical data, automated multi-document biomedical text summarization becomes an effective and robust approach of accessing the increased amount of technical and medical literature in the biomedical sector through the summarization of multiple source documents by retaining the significantly informative data. So, multi-document biomedical text summarization acts as a vital role to alleviate the issue of accessing precise and updated information. This paper presents a Deep Learning based Attention Long Short Term Memory (DL-ALSTM) Model for Multi-document Biomedical Text Summarization. The proposed DL-ALSTM model initially performs data preprocessing to convert the available medical data into a compatible format for further processing. Then, the DL-ALSTM model gets executed to summarize the contents from the multiple biomedical documents. In order to tune the summarization performance of the DL-ALSTM model, chaotic glowworm swarm optimization (CGSO) algorithm is employed. Extensive experimentation analysis is performed to ensure the betterment of the DL-ALSTM model and the results are investigated using the PubMed dataset. Comprehensive comparative result analysis is carried out to showcase the efficiency of the proposed DL-ALSTM model with the recently presented models.

show abstract

Unsupervised neural networks for automatic Arabic text summarization using document clustering and topic modeling

Cited by 45 publications

References 41 publications

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Type2 IFC with SOA for Topic Detection and Document Clustering Analysis

Automated Multi-Document Biomedical Text Summarization Using Deep Learning Model

Contact Info

Product

Resources

About