Transliteration Process Research Articles

Machine Transliteration of Handwritten MODI Script to Devanagari using Deep Neural Networks

The transliteration process involves transcribing words from the source language into the target language that uses a different script. Language and scriptural hurdles can be overcome via transliteration systems. There is a demand for automated transliteration systems due to the existence of several languages and the growing number of multilingual speakers. This study focuses on the Machine Transliteration of handwritten MODI script to Devanagari. MODI script was the official script for Marathi till 1950. Although Devanagari has, since then, taken over as the Marathi language's official script, the MODI script has historical significance as large volumes of its manuscripts are preserved in libraries across different parts of India. However, MODI into Devanagari transliteration is a difficult task because MODI script documents are complex in nature and there is no standard dataset available for the experiment. Machine Transliteration can be approached either as a Natural Language Processing task or as a pattern recognition task. In this research work, the transliteration task is carried out using the pattern recognition technique. The transliteration of MODI script to Devanagari is implemented using Convolutional Recurrent Neural Network (CRNN) based Calamari OCR, which is open-source software. An accuracy of 88.14% is achieved in character level matching of each word in the MODI to Devanagari transliteration process. When considering the entire word matching, the accuracy achieved is 61%. Machine Transliteration of

TAMZHI: Shorthand Romanized Tamil to Tamil Reverse Transliteration Using Novel Hybrid Approach

Transliteration from Tamil to the Roman script holds a crucial place in the realms of effective communication, educational accessibility, and the seamless integration of digital technology. However, this process encounters a significant challenge due to the disparity in the number of vowels between the Tamil script, which encompasses a rich set of 12 vowels, and the Roman script, which is limited to just 5. This incongruity poses a substantial impediment when attempting ad-hoc transliteration of Tamil into the Roman script, especially when vowels are omitted. This paper aims to make a significant academic contribution by conducting an extensive literature review of recent developments in Romanized Tamil to Tamil transliteration, with a particular focus on addressing the absence of vowels. The review involves a meticulous examination of a wide array of methodologies proposed in recent years, ranging from rule-based systems to context-based strategies and machine learning-based approaches. In response to the challenges inherent in Tamil to Roman transliteration, this research work introduces a novel and innovative solution. This solution incorporates a Reverse Transliteration module, which leverages N-gram analysis and a rule-based model. The utilization of a trained trie structure is a key component of this approach, enabling word suggestions that effectively resolve ambiguities during the transliteration process. Remarkably, the proposed solution outperforms existing character-level transliteration methods, achieving an impressive character-level accuracy rate of 0.93. The practical implications of this research are substantial, particularly concerning the fulfilment of the linguistic and transliteration needs of native Tamil speakers within the digital platform, where such accuracy is of utmost importance.

Transliteration of Arabic Words/Phrase into English: An Exploration of Ambiguity Markers

Transliteration is a useful process when communication involves a language pair out of which each follows a different script, such as Arabic and English. One danger posed by this process is the ambiguity between the source and target of the communication. This study analyzes the intricate process of Arabic to English transliteration and the factor that make it ambiguous. The study aims to identify, categorize, and analyze the ambiguity markers that frequently arise during the transliteration of Arabic script into the Latin alphabet. The study interviewed 6 specialist translators in the Saudi context to identify the source of difficulties they encounter and which may bring ambiguities to the readers at various language levels. Results indicated that non-standardization in translation from Arabic to English was a cause of ambiguity in transliteration. Finally, regional dialects could not be adjusted in the transliteration spectrum in Google Translate. This research contributes to the field of transliteration studies by providing a comprehensive framework for understanding and addressing ambiguity in the transliteration process.

Averroes and St. Thomas Aquinas Debate: How the Moslem Philosopher Understanding Aristotle Philosophy about Soul and Intellect

Arabs have penetrated the joints of Europa thought through a process of transliteration involving Islamic philosophers. While medieval Europe was a dark age, Arabs provided opportunities and space for the transliteration of the works of Plato and Aristotle. Thinkers (Islamic philosophers) penetrated the joints of European thought through the process of transliteration, one of which was Averroes, who attempted to re-perceive the soul and intellect of Aristotle, which later differed from the understanding built by St. Thomas Aquinas. From their position as Islamic philosophers, Averroes and St. Thomas Aquinas as Christian philosophers, their faith interests also enriched the conflict over the understanding of Aristotle's philosophy, especially about soul and intellect.

Phonetic-Based Forward Online Transliteration Tool from English to Tamil Language

Transliteration is the process of mapping the character of one language to the character of some other language based on its phonetics. India is very much diverse in languages where people speak different languages. Though they speak different languages, it might be difficult for them to read the script of those many languages. In a situation like this, transliteration process plays a major role. It helps in various Natural Language Processing applications such as Information retrieval, Machine translation, Speech recognition. These are NLP applications which make the computer understand the natural language as to how human being interprets. It helps in translating technical terms and proper names from one language to another language. Moreover, transliteration works have been carried out in languages such as Japanese, Chinese and English. But when considering Indian languages, especially Tamil language, very few recognizable works have been carried out. In this paper, transliteration process is carried out on Unicode Tamil characters. The phonetics-based forward list processing is implemented for transliterating from English language to Tamil language which yields promising results.

La deconstrucción ayer y hoy : de la escritura a la plasticidad

Jacques Derrida re-signified the concept of writing, which passed from referring to the simple description of the process of transliteration of the voice, to a phenomenon of inscription of sense prior to any sign. This conceptual extension forged the foundations of deconstruction. This article analyses the central approaches of Derrida’s philosophical project and reflects on the outcome of the philosophy of (arche)writing in the current context of the renewal proposed by the new materialisms and, specifically, by Catherine Malabou’s project.

Forward-backward Transliteration of Punjabi Gurmukhi Script Using N-gram Language Model

Transliterating the text of a language to a foreign script is called forward transliteration and transliterating the text back to the original script is called backward transliteration. In this work, we perform both forward as well as backward transliteration on Punjabi. We transliterate Punjabi person names from Gurmukhi script to English Roman script and from English Roman script back to Gurmukhi script using n-gram language model. We used more than one million parallel entities of person names in Gurmukhi and Roman script as the training corpus. We generated English to Punjabi and Punjabi to English n-grams databases from the corpus. To get better results, we tried to create as long n-grams as possible ranging from bi-gram to 30-gram. Our n-grams database contains more than 10 million n-grams, with each n-gram having multiple mappings of the other script. The most challenging part is to find the mapping for the given n-gram from the parallel name entity while creating n-grams databases. As per the orthography rules, the same combination of letters may have different pronunciation, depending upon its location in the word. Therefore, we categorized n-grams into starting, middle, and ending n-grams and used them accordingly in the transliteration process. The transliteration process works like the merge sort. We start searching the longest possible n-gram in the database and split the string recursively until the match is found. The transliterated strings are merged back to form the final output. In English to Punjabi transliteration, we achieved 96% accuracy using gold standard and 99.14% accuracy using minimum edit distance. In Punjabi to English transliteration, the result showed 96.85% and 99.35% accuracy for the gold standard and minimum edit distance, respectively.

Transliteration of Indonesian Geographical Names into Chinese

In this paper, a comparative analysis of the phonetics between Indonesian and Chinese in the geographical name conversion process is carried out to investigate the way of Chinese transliterating for Indonesian geographical names, in order to standardize Chinese proper translation for Indonesian geographical names. The author found that in general, people will translate geographical names by transliterating for specific parts of the name, and paraphrasing for generic names. Processing of vowels and consonants has different characteristics in the transliteration process, which generally according to Chinese pronunciation habits. And some geographical names are translated directly into Chinese dialects. This contains a wealth of immigrant cultural information and dialect information, which can infer the general distribution of early Chinese immigrants in Indonesian settlements, guide significance for the study of Chinese society and culture. In addition, Chinese transliterated names for Indonesian geographical names in different historical periods are subject to change.

HUKUM VIRAL PADA NASKAH HIDAYATUS SALIKIIN KARANGAN SYEKH ABDUSSAMAD AL-FALAMBANI ( KAJIAN SEMANTIK )

This research examines old Malay manuscripts about Hubbil jaahi (Love for splendor) or famous/want to be known (viral) opinion of Hujjatul Islam (Imam al-Ghazali ra) in the manuscript Hidayatus saalikiin Manuscript written by Syekh Abdussamad al-falambany, this study aims so that humans do not stuck with ria and ujub and hypocrisy. ¬The original manuscript is in Arabic Malay pegon. This research uses the semantic theory of qualitative descriptive analysis beginning with the process of transliteration from Jawi script to Latin script and relevant studies. This study is very important to examine more deeply, the causes and effects of wanting to be known (viral). So be careful in doing good, Allah is all-knowing to people who don't know and this understanding is truly glorious if it is informed to the general public so that they are safe from the practices of Ria and ujub, as far away from hypocrisy as possible.

Machine-Based Transliterate of Ottoman to Latin-Based Script

In this paper, a machine-based transliterate is presented. The automatic transliteration of Ottoman to the modern Latin Turkish script can open a big window for scientists in fields of history and literature while most of the Turkish people are not familiar with Ottoman script, despite the fact that no concrete solution has been proposed yet for this issue. The proposed method includes several steps since the transliteration process of Ottoman alphabet to Latin base consists of many problems; the first is the basic character mapping which covers the regular pronunciation and orthography mapping. On the other hand, covering other irregular and extraordinary cases is based on rules and normalization. The transliteration system achieved 73.9% accuracy in general.

A review of existing transliteration approaches and methods

ABSTRACT The article highlights the importance of transliteration in the field of machine translation, correct writing of personal and place names, and information retrieval. It provides an overview of various approaches, models and methods available in the field of transliteration. It shows the types of transliteration methods. The article also highlights the principles taken into account during the process of transliteration. It shows advantages and disadvantages of the proposed transliteration methods for different languages. It explains the accuracy of mentioned transliteration techniques through transliterated words. It is noted that proposed transliteration methods for one language may not be significant for others. Moreover, it may not be enough to apply only one method in the field of direct and backward transliteration of languages with different graphemes and phonemes. Therefore, different transliteration techniques have to be combined.

Neology of Arabic in Indonesia

The development of Arabic which is influenced other language and culture is very interesting to be discussed, because Arabs themselves are not able to give a name to something that does not exist in their nature and their thought, such as naming cases, and terms that come from language and nature of thought of Indonesians. Many of these new words and terms have been featured in one of the Arabic language magazines which is Alo Indonesia. This study aims to find out how the names and terms in Indonesian discourse influenced Arabic and the problems that arise in the process of producing words in the magazine. This research is literature research that used descriptive methods, namely describing the data by concerning to how the use of new Arabic words and terms in Alo Indonesia magazine. The data collection method is done by using the “note-taking” technique which is then collected in the data card. To answer the two main problems above, the writer used Ibrahim Murad's theory of neology. The findings of this study shows that according to five theories by Ibrahim Murad, Alo Indonesia magazine uses more semantic neology theory (al-Taulĩd al-Dalalĩ) and loan neology (al-Taulĩd bi al-Iqtirād). The biggest problem in the transliteration process from Indonesian letters into Arabic is that not all vowels and consonants in Indonesian are also available simultaneously in Arabic, and so does the difficulty of finding the equivalent of idea in the expression of these two languages.

Penerapan Algoritma Rule Base dengan Pendekatan Hexadesimal pada Transliterasi Aksara Bima Menjadi Huruf Latin

Aksara Bima is a text-based information exchange media that has never been lost. At this time the Bima script began to be studied again indicated, with researchers who began to explore the history and stages of the process of digitizing the characters including the Bima script. Thus providing hope for the use of characters in community activities. One problem faced when wanting to learn the characters felt by the community is the different forms of characters in Latin letters and there are fixed rules when writing characters that make the process of writing characters feel difficult. So the writing of characters in daily activities in community activities still cannot be said to be massive due to these problems. In this study, the writer will develop an algorithm that can facilitate the learning activities of characters, which is specialized in the process of reading the Bima Script. The method adopts the concept of machine learning that is applied to the process of transliteration of Bima, into Latin letters. With a string replacement algorithm that is optimized by using hexadecimal numbers. The results obtained from this transliteration process in the form of system accuracy that reaches 90.64% of 171 implemented rule base.

The Challenges of Azerbaijani Transliteration on the Multilingual Internet

Several scripts have been adopted so far in Azerbaijan in different periods. Literary manuscripts and political documents developed in each of the adopted scripts are of great importance and have to be transliterated for the next generation. However, adoption of different scripts and their frequent changes lead to the emergence and dissemination of various transliteration versions on the web. This article touches upon the challenges of Azerbaijani-English transliteration process in real life and online. In this regard, the significance and dominating status of the English language on the Internet and throughout the globe is explored. Adoption of a unique transliteration standard for Azerbaijani language may contribute to the solution to this problem. The standards for the transliteration of the Azerbaijani language with others are analyzed, and the inevitability of a new approach to Azerbaijani-English transliteration is emphasized. Moreover, the article underlines future contribution of the proposed transliteration system for machine translation system of Azerbaijani-English language pair.

THARIQAH AT TATHBIQIY LI TARJAMAH KUTUB AL TURATS FI MUASSASAH DIRASAH AL QURAN WA KITAB AL TURATS SURABAYA

Arabic language has some effects for governing Islamic knowledge, furthermore the first source Islamic knowledge is al-Qur’an and al-Hadits that used arabic language. If we want to govern it, we must know arabic language. Usually turast book was studied in Islamic boarding school for understanding some religion knowledges from al-qur’an and al-hadits. For understanding turast book we have to pass transliteration process. It will be find the conclution from the Islamic knowledge. One of way to ease the student for transliting arabic books is tatbiqi methode. It’s combine arabic gramatical, learning vocabularies, and transliting process. The student not only learn the arabic gramatical, but also practice to translate arabic texts according to the principle was learned .

A Computerized Reversible Arabic Transliteration System

Most of the available transliteration/Romanization systems from Arabic to English contain inconsistencies and lack both standardization and reversibility. They do not account for a reciprocal transliteration process from Arabic to English and vice versa. It can also be noticed that some lexical items are spelled in different ways as a result of an inconsistent transcription of the Arabic version. This is illustrated by instances such as ( : s, c, w), ( : z), ( : j), ( : x, c) and ( : z). The reason is that most transliteration users are often trained neither practically nor theoretically in the science of linguistics and phonetics. The symbols are often chosen in an ad hoc manner and vary from one scholar to another. The objective of this research is thus twofold. On the one hand, it seeks to develop a scholarly standard/mechanism to represent the Arabic letters in order to provide a homogenous transliteration system and, on the other hand, to develop a mobile-based application to serve the purpose of a logical and reversible inter-language tool which will be applied for transliteration at large and for Quranic terminological sciences in particular. That system shall be referred to as NOOR-TR. In doing so, initially, a comparison between various platforms is made followed by a proposal of a homogenizing symbolization which will be, then, engineered into a reliable and reversible application.

Relevansi Dan Penerapan Subject Authority dalam Sistem Temu Kembali Koleksi Kitab Kuning Pusat Perpustakaan UIN Maulana Malik Ibrahim Malang

This research describe about how relevation and subject authority implementation on yellow book collections in retrieval system UIN Maulana Malik Ibrahim Library Center Malang. Background in this research is from the past researchs and because UIN Maulana Malik Ibrahim Library Center Malang based from Islamic and have so many book collections. In this library have a different wisdom to managing book collections and general collections. Result from this research is : (1) relevansion rank yellow book collections in retrieval system UIN Maulana Malik Ibrahim Library Center Malang from subject authority method are low and not effective and ideal and then bring out recall 70% and precision 58.3%. (2) implementation process on subject authority yellow book collections UIN Maulana Malik Ibrahim Library Center Malang are not match with implementation principal, and have a result: there are not consistent using a subject (from 97 sample, 37 sample are not consistent), vocabulary index subject implementation don’t have a control language (from 97 sample, 56 are not controlling), using original name versus foreign is lack of attention (from 74 subject, there some Arabic name are not consistent with Arabic-Indonesian transliteration process) and subject authority implementation are not focus with primary books (in 16 book collections)

Hindi to Punjabi Transliteration using Phonetic and Orthographic Rules

One of the important applications of Natural Language Processing is machine translation. Machine transliteration is an emerging and a very important research area in the field of machine translation. Translation systems translate message from source language to target language, keeping the exact meaning. While the transliteration system finds the same meaning word/sentence in another language, the transliteration helps us to pronounce them. This paper addresses the transliteration process from Hindi to Punjabi language using a rule based approach. Transliteration is more phonetic process, thus both source grapheme and its sound in the correct pronunciation of word have been considered for rule formation to achieve high performance and more accurate results. The system is tested on news domain text and achieved accuracy of 97%.

Review of Machine Transliteration Techniques

is the conversion of a text from one script to another, and thus representing words from one language using the approximate phonetic or spelling equivalents of another language. Machine Transliteration has come out to be an emerging and a very important research area in the field of machine translation. Transliteration systems are very beneficial for removing the language and scriptural barriers. It has gained prime importance as a supporting tool for machine translation and cross-language information retrieval, especially when proper names and technical terms are involved. Various techniques are available for transliteration process. This paper is intended to give a brief overview of commonly used machine transliteration techniques.

The translation of names and the fallacy of representation – and the creative consequences for literary translation in the Chinese-English context

The translation of names is often assumed to be a process of transliteration, where letters and the sounds they constitute can be directly transplanted or accurately converted from one language to another with little or no ambiguity. This is a logical generalization if one considers that the top ten source and target languages of translation are frequently occupied by the likes of English, French, German, Spanish, Russian, and Japanese. However, an examination of the Chinese names of foreigners – and, equally, the English names of Chinese – will reveal that the objective representation of the Other is anything but. Not only does a name bear the identity of a person, it also belies the authority of the namer and the ideology behind the choice of words. What is often articulated and argued in the name of “accuracy” or “objectivity” or any other standard is, in actuality, a manifestation of ethnocentrism, facilitated by the ideology of translation, which presents the act as a transparent, interest-free means of “cultural” communication. What needs to be exposed is the agency behind the act, not its “accuracy” or “objectivity” or lack thereof. Allowing agency – to the Chinese subject choosing an English name, to the translator translating a Chinese name into English – is showing respect to the foreign, while “representation,” on the other hand, is almost always an argument made on behalf of the silent subject. For the literary translator, this means that dutifully transliterating the name “明明” as “Mingming” according to Pinyin does not necessarily make it a more authentic representation of what is “Chinese”; nor does calling her “Claire” make her any less “Chinese” than what she already is. What is at stake here is which name best functions in accordance to the literary design and the intentions of the translator – in alignment with his or her interpretation of the text. The failure to see past the fallacy which automatically deems the Pinyin spelling to be correctly “Chinese” and “Claire” to be incorrectly “Western” will result in a translation that is perhaps good for indexing purposes, but ultimately dull and one-dimensional for interpretative ones. If the translator is denied the creation of a text that allows for multiple readings, then the battle for this profession’s higher status – aesthetically, commercially, legally – is a losing one.