International Journal of Computer Applications (0975 – 8887) Volume 133 – No.15, January 2016 36 Translation Challenges and Universal Networking Language Baljeet Kaur Dhindsa Assistant Professor Guru Gobind Singh College for Women Sector 26, Chandigarh, India Dharam Veer Sharma Associate Professor Department of Computer Science Punjabi University, Patiala, India ABSTRACT This paper presents challenges being faced in designing automatic translation software. There are many approaches to automatic translation like Direct, Rule based, Transfer based, Statistical based and Interlingua. A brief description of all the approaches and their advantages and drawbacks are discussed. Universal Networking Language (UNL) based on Interlingua approach can be used especially for translation among multiple languages because it requires knowledge of UNL and of the language which user wants UNL to support. User can then get translated text in any of the languages supported by UNL without even being oblivious to any other language. It is less expensive approach also. This paper also gives brief introduction to UNL and how it can overcome many of the challenges in translation. Keywords Machine Translation, Machine Translation Approaches, Interlingua, Challenges in Machine Translation, Universal Networking Language, Overcoming challenges in Machine Translation using UNL. 1. INTRODUCTION Language is one facet that discerns man from all other species on the earth, because it is one asset that no other creature possesses. On one hand, it allows a man to express himself and on the other, it facilitates him in gaining knowledge. Knowledge is assumed to be a service to mankind as it results in new ideas, new information and it helps in acquiring more knowledge also. There are numerous languages in the world and India is linguistically diverse country as according to 2001 census, there are 22 constitutionally scheduled languages, 100 mother tongues and approximately 1000 documented languages and dialects. India is a country which symbolizes unity in diversity. According to Marc Twain, India is the place where human languages originated, history evolved, legends born, and diverse cultures developed. Multiple languages give language freedom to its people, but it also results in perplexity among masses due to usage of different languages in different parts of the same country. Freedom of language is the birthright of every individual, so to overcome with the problems due to multiple languages, few simple measures can be taken. One of the best possible solutions, in the current era of technological revolution can be providing tools which can translate data into the language of the user. The word Translation means converting text, written/spoken, from one language to another. For communication among people with different linguistic usage, there arises a need to translate written/spoken language of one group of people for understanding by the other group who are trying to communicate with one another. For effective communication, two people need to understand each other‟s language appropriately either by using the same language or by using a mediator who can translate language used by one person to another person‟s language. Communication between sender and receiver group(s) is incomplete if the receiver does not understand the information from the sender effectively in the context in which it has been communicated. Human translators are doing translation among group of people having different language of communication since centuries. Although human translators are impeccable in their performance, yet scarcity of translation specialists is a problem for the growing translation markets around the world. However, with the advancement in technology, this process has become automated to some extent. Translation nowadays is not restricted to communication of one‟s ideas only, but it is required by people for expansion of their business also. Automatic Machine Translation is conversion of text from one language to another by using a machine. Many automatic translation procedures are in use these days. Some of these automatic machine translators need human intervention for effective translation while some are capable of doing it automatically. Due to increase in demand of translation and that too at faster speed as well as in multiple languages simultaneously, machine translation has become a necessity in today‟s fast paced global interactions. Although the study and development of automatic language translators has been going on since 1947 [18], yet it is becoming an increasingly important topic for researchers due to increased requirement of communication in the era of globalization and use of numerous languages worldwide. 2. CHALLENGES IN TRANSLATION Translating written text can pose several challenges which are illustrated as follows: 2.1 Language Structure Languages can be differentiated in the way they order words in sentences; some languages follow SOV (Subject-Object- Verb) structure like Hindi, Punjabi, Hungarian, Turkish, Japanese etc.; while some follow SVO (Subject-Verb-Object) like English, Malay, Germanic, Thai etc. Some languages follow VSO structure like Irish, Arabic, Hebrew etc. [7] and very few languages follow VOS structure like Palauan, Tzotzil [12]. Translation may become difficult when a sentence in source/target language follows one type of structure and in target/source language follows another. 2.2 Translate or Transliterate This is another challenge in translation field that how to decide whether a word in source language is to be translated or transliterated, where transliteration means representing word given in source language into a word in target language, in which the character set of the target language only need to be used, keeping the pronunciation of the original word intact. Some words in a sentence are required to be translated, whereas some words do not need to be translated but rather transliterated like name of countries, states, people, places, organizations etc. In some cases it becomes difficult to make such a differentiation among words. For example, a simple