On the development of name search techniques for Arabic

Aqeel, Syed; Beitzel, Steve; Jensen, Eric C.

doi:10.1002/asi.20323

Cited by 18 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extra characters { ‫ؤ‬ , ‫ئ‬ , ‫ة‬ } were converted ‫‖ة-‬ to -‫ه‬ , " " ‫ؤ‬ ‖ to ‫‖,و-‬ and ‫‖ئ-‬ to ‫‖ي-‬ in our manual mapping for the PIM project [11]. Reference [10] mentioned an exact Arabic Soundex table, and another Arabic Soundex table is called ASoundex, which has one character ‫)ﻅ(‬ in a different group [12]. Table II represents the Arabic table generated by our automated tool.…”

Section: B Mapping Resultsmentioning

confidence: 99%

Character Mapping for Cross-Language

Al-Shuaili¹,

Carvalho²

2016

IJFCC

View full text Add to dashboard Cite

Abstract-Out-of-vocabulary words are a significant challenge for cross-language information retrieval. Names of people constitute a large portion of out-of-vocabulary words, as there are different methodologies to match names that are written in various languages. Some of the methods convert names to phonetic codes, such as Soundex, or transliterate names from one language to another. We propose a technique to map characters automatically from different languages into English, without human interference and without prior knowledge of the language. This technique can provide a statistical or phonetic model that can be used later for name comparisons or named transliterations into a cross-language. The method also generates Soundex codes for the source language based on English Soundex codes. We implement this technique for five languages: Arabic, Russian, Urdu, Hindi, and Persian. Five Soundex tables are provided as the result of this technique.

show abstract

Section: B Mapping Resultsmentioning

confidence: 99%

Character Mapping for Cross-Language

Al-Shuaili¹,

Carvalho²

2016

IJFCC

View full text Add to dashboard Cite

show abstract

“…That is why, we decided to improve the last method by indexing the words by their pronunciation or more exactly by their representative sounds. For that, we used Soundex [14], a phonetic algorithm for indexing by sound. Words are encoded by taking advantage of their phonetic form.…”

Section: Indexing Words By Their Soundsmentioning

confidence: 99%

CALYOU: A Comparable Spoken Algerian Corpus Harvested from YouTube

Abidi¹,

Menacer²,

Smaïli³

2017

Interspeech 2017

View full text Add to dashboard Cite

This paper addresses the issue of comparability of comments extracted from Youtube. The comments concern spoken Algerian that could be either local Arabic, Modern Standard Arabic or French. This diversity of expression gives rise to a huge number of problems concerning the data processing. In this article, several methods of alignment will be proposed and tested. The method which permits to best align is Word2Vecbased approach that will be used iteratively. This recurrent call of Word2Vec allows us improve significantly the results of comparability. In fact, a dictionary-based approach leads to a Recall of 4, while our approach allows one to get a Recall of 33 at rank 1. Thanks to this approach, we built from Youtube CALYOU, a Comparable Corpus of the spoken Algerian.

show abstract

“…There are more than four hundred million Arabic language speakers who live in 22 countries from the Arabian Peninsula across North Africa to the Atlantic Ocean [15]. Arabic is the main language of newspapers, TV news, books, and official works, even though there are different accents across countries and even within countries.…”

Section: Arabic-to-english Mappingmentioning

confidence: 99%

Personal Identity Matching

Al-Shuaili¹

2016

Computer Science &Amp; Information Technology ( CS &Amp; IT )

View full text Add to dashboard Cite

Despite all existing methods to identify a person, such as fingerprint, iris, and facial recognition, the personal name is still one of the most common ways to identify an individual. In this paper, we propose two novel algorithms: The first one uses sound techniques to create a multi-dimensional vector representation of names to compute a degree of similarity. This algorithm compares names that are written in different languages (cross-language) and transliterated names in English. The second algorithm builds on the first one and measures the similarities between full names, taking into account the full name structure. We evaluate the algorithms for transliterated names and across languages using Arabic and English as an example. Significant results are achieved by both algorithms compared with other existing algorithms.

show abstract

On the development of name search techniques for Arabic

Cited by 18 publications

References 19 publications

Character Mapping for Cross-Language

Character Mapping for Cross-Language

CALYOU: A Comparable Spoken Algerian Corpus Harvested from YouTube

Personal Identity Matching

Contact Info

Product

Resources

About