An Approach for Extracting and Disambiguating Arabic Persons’ Names Using Clustered Dictionaries and Scored Patterns

Zayed, Omnia; El-Beltagy, Samhaa R.; Haggag, Osama

doi:10.1007/978-3-642-38824-8_17

Cited by 5 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are becoming increasingly critical in a variety of applications such as machine reading and understanding, intelligence analysis, social media analysis, etc. [5,6]. The diversity of domains which rely on NLP (e.g., news media, law, biomedicine, pharmaceutical/pharmacogenomics, chemistry, etc.…”

Section: Entity Extractionmentioning

confidence: 99%

“…In supervised ML, to classify entities, a model is trained on an annotated (manually tagged by human experts) set of documents (corpus). The semi-supervised ML is a hybrid system that uses a combination of annotated and non-annotated data, machine learning, and rule-based approach [6]. To improve the training process, human experts are selectively given training examples to label while other training examples are automatically labeled by the machines [19,21].…”

Section: Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

Developing an innovative entity extraction method for unstructured data

Zaghloul¹,

Trimi

2017

Int J Qual Innov

View full text Add to dashboard Cite

The main goal of this study is to build high-precision extractors for entities such as Person and Organization as a good initial seed that can be used for training and learning in machine-learning systems, for the same categories, other categories, and across domains, languages, and applications. The improvement of entities extraction precision also increases the relationships extraction precision, which is particularly important in certain domains (such as intelligence systems, social networking, genetic studies, healthcare, etc.). These increases in precision improve the end users' experience quality in using the extraction system because it lowers the time that users spend for training the system and correcting outputs, focusing more on analyzing the information extracted to make better data-driven decisions.

show abstract

Section: Entity Extractionmentioning

confidence: 99%

Section: Machine Learningmentioning

confidence: 99%

Developing an innovative entity extraction method for unstructured data

Zaghloul¹,

Trimi

2017

Int J Qual Innov

View full text Add to dashboard Cite

show abstract

“…There is no fixed standardization for writing the word like English. For example, the word " ‫جراً‬ ", jrAm1, "Gram", can also be written as ‫"غراً‬ ", grAm, with the same meaning, also the word ‫جٌجو‬ / Google can be written as ‫,غٌغو‬ other example the word ‫سٌريب‬ / Syria can be written as ‫سٌريخ‬ [1,2,22]. …”

Section: ) Lack Of Capital Lettersmentioning

confidence: 99%

“…In [22] the authors developed their system in [28]. They used integrated approach: a) name dictionaries and b) name clusters with a statistical model based on extracting patterns that indicate the existence of person's names.…”

Section: Related Workmentioning

confidence: 99%

“…However, Arabic lack the capital letter, so the detection of NE in text based on the letters case more difficult. The lexical triggers used to overcome this problem, which has used that are derived from analyzing the surrounding context of NEs while some others researchers have used the English translation of the NE what is known as the glossing feature produced by the MADA tool [2,3,22].…”

Section: ) Lack Of Capital Lettersmentioning

confidence: 99%

See 1 more Smart Citation

Integrating Semantic Features for Enhancing Arabic Named Entity Recognition

Alsayadi¹,

El-Korany²

2016

ijacsa

View full text Add to dashboard Cite

Abstract-Named Entity Recognition (NER) is currently an essential research area that supports many tasks in NLP. Its goal is to find a solution to boost accurately the named entities identification. This paper presents an integrated semantic-based Machine learning (ML) model for Arabic Named Entity Recognition (ANER) problem. The basic idea of that model is to combine several linguistic features and to utilize syntactic dependencies to infer semantic relations between named entities. The proposed model focused on recognizing three types of named entities: person, organization and location. Accordingly, it combines internal features that represented linguistic features as well as external features that represent the semantic of relations between the three named entities to enhance the accuracy of recognizing them using external knowledge source such as Arabic WordNet ontology (ANW). We introduced both features to CRF classifier, which are effective for ANER. Experimental results show that this approach can achieve an overall F-measure around 87.86% and 84.72% for ANERCorp and ALTEC datasets respectively.

show abstract