KEFST: a knowledge extraction framework using finite-state transducers

Mahmood, Ahsan; Khan, Hikmat Ullah; Rehman, Zahoor Ur; Iqbal, Khalid; Faisal, Ch. Muhmmad Shahzad

doi:10.1108/el-10-2018-0196

Cited by 7 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic Keyword Extraction, Named Entity Detection such as person names, geographical names, dates and times and extracting them from the content of hadiths as well as other applications like segmentation the text of long hadiths, summarization of hadiths, translations and commentaries related to them, all belong to this group. [95]- [98]…”

Section: B Hadith Contentmentioning

confidence: 99%

Artificial Intelligence and Modern Information Technologies Applications in Islamic Sciences: A Survey

Rabiei Zadeh

2023

IJPCC

View full text Add to dashboard Cite

Considering the progress of Artificial Intelligence (AI) and the Information Technology (IT) we witness, during recent years, the spread of the application of these technologies in various fields. The research workflows, and in particular, the researches on Islamic sciences are not excepted from this issue. Several works have been carried out in order to exploit the AI and modern information technologies in the researches on Islamic sciences during recent years all over the Islamic regions and beyond them. It is very important to be aware of the latest developments in this field from different aspects like: 1) Benefiting from the advantages of modern technologies in the Islamic researches, 2) Reorganizing the educational plans in accordance with these developments, and 3) Introducing the new applications of AI in Islamic studies to the academics of computer sciences who may be interested in this field. In this paper, in the first step, a systematic review was conducted concerning more than four thousand international scientific articles related to applying AI and modern IT in Islamic studies, out of which 975 ones were chosen. At the same time, major institutions in this field were identified. In the next step the selected articles were classified in five thematic fields of 1) the Holy Qur’an, Tafsir and other related issues, 2) Hadith and Rijal Sciences, 3) Islamic Law and Jurisprudence, 4) the General Islamic Content in Social Media, 5) Other Subjects related to Islamic Sciences like Linguistics, History, Geography, etc. In the third step, the articles of each category were classified in a number of major subcategories that amount to 73 in total. Finally, in the last step, the distinctive articles in each field were introduced briefly.

show abstract

Section: B Hadith Contentmentioning

confidence: 99%

Artificial Intelligence and Modern Information Technologies Applications in Islamic Sciences: A Survey

Rabiei Zadeh

2023

IJPCC

View full text Add to dashboard Cite

show abstract

“…The results indicate that the classifiers' combination technique achieves the best performance, with precision, recall, and F-Measure values of 96.9 percent, 93.6 percent, and 95.3 percent, respectively. Another author [6] built a NER-based knowledge extraction framework that employs finite-state transducers (FSTs) -KEFST -to extract the Hadith Narrators from the Urdu Translation Hadith text. KEFST consists of five steps: content extraction, tokenization, part of speech tagging, multi-word detection, and NER.…”

Section: Related Workmentioning

confidence: 99%

BERT based Named Entity Recognition for Automated Hadith Narrator Identification

Luthfi¹,

Yusoh²,

Aboobaider³

2022

IJACSA

View full text Add to dashboard Cite

Hadith serves as a second source of Islamic law for Muslims worldwide, especially in Indonesia, which has the world's most significant Muslim population of 228.68 million people. However, not all Hadith texts have been certified and approved for use, and several falsified Hadiths make it challenging to distinguish between authentic and fabricated Hadiths. In terms of Hadith science, determining the authenticity of a Hadith can be accomplished by examining its Sanad and Matn. Sanad is an essential aspect of the Hadith because it indicates the chain of the Narrator who transmits the Hadith. The research reported in this paper provides an advanced Natural Language Processing (NLP) technique for identifying and authenticating the Narrator of Hadith as a part of Sanad, utilizing Named Entity Recognition (NER) to address the necessity of authenticating the Hadith. The NER technique described in the research adds an extra feed-forward classifier to the last layer of the pre-trained BERT model. In the testing process using Cahya/bert-base-indonesian-1.5G, the proposed solution received an overall F1-score of 99.63 percent. On the Hadith Narrator Identification using other Hadith passages, the final examination yielded a 98.27 percent F1-score.

show abstract

“…In the cultural heritage textual context (interviews), a methodology for automatic annotation of a multimedia collection of intangible cultural heritage was proposed (Tanasijević and Pavlović-Lažetić, 2020). Text-based entity relation extraction research also addressed unique challenges associated with extending knowledge from a single language context to a cross-lingual context (Mahmood et al , 2019; Tomašević et al , 2018; Yu et al , 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Framework for entity extraction with verification: application to inference of data set usage in research publications

Nestorov

Bačić

Jukić

et al. 2022

View full text Add to dashboard Cite

Purpose The purpose of this paper is to propose an extensible framework for extracting data set usage from research articles. Design/methodology/approach The framework uses a training set of manually labeled examples to identify word features surrounding data set usage references. Using the word features and general entity identifiers, candidate data sets are extracted and scored separately at the sentence and document levels. Finally, the extracted data set references can be verified by the authors using a web-based verification module. Findings This paper successfully addresses a significant gap in entity extraction literature by focusing on data set extraction. In the process, this paper: identified an entity-extraction scenario with specific characteristics that enable a multiphase approach, including a feasible author-verification step; defined the search space for word feature identification; defined scoring functions for sentences and documents; and designed a simple web-based author verification step. The framework is successfully tested on 178 articles authored by researchers from a large research organization. Originality/value Whereas previous approaches focused on completely automated large-scale entity recognition from text snippets, the proposed framework is designed for a longer, high-quality text, such as a research publication. The framework includes a verification module that enables the request validation of the discovered entities by the authors of the research publications. This module shares some similarities with general crowdsourcing approaches, but the target scenario increases the likelihood of meaningful author participation.

show abstract

KEFST: a knowledge extraction framework using finite-state transducers

Cited by 7 publications

References 22 publications

Artificial Intelligence and Modern Information Technologies Applications in Islamic Sciences: A Survey

Artificial Intelligence and Modern Information Technologies Applications in Islamic Sciences: A Survey

BERT based Named Entity Recognition for Automated Hadith Narrator Identification

Framework for entity extraction with verification: application to inference of data set usage in research publications

Contact Info

Product

Resources

About