The Serbian Language in the Digital Age — Executive Summary

During the last 60 years, Europe has become a distinct political and economic structure, yet culturally and linguistically it is still very diverse. From Portuguese to Polish and Italian to Icelandic, everyday communication between Europe’s citizens as well as communication in the spheres of business and politics is inevitably confronted by language barriers. The EU’s institutions spend about a billion euros a year on maintaining their policy of multilingualism, i.e., translating texts and interpreting spoken communication. Yet does this have to be such a burden? Modern language technology and linguistic research can make a significant contribution to pulling down these linguistic borders. When combined with intelligent devices and applications, language technology will in the future be able to help Europeans talk easily to each other and do business with each other even if they do not speak a common language.

Major trade partners of Serbia come from the EU, with a share of over 50% in its total trade, while exports to the EU market are free-of-customs according to the Stabilisation and Association Agreement. But language barriers can bring business to a halt, especially for SMEs who do not have the financial means to reverse the situation. The only (unthinkable) alternative to this kind of multilingual Europe would be to allow a single language to take a dominant position and end up replacing all other languages.

One classic way of overcoming the language barrier is to learn foreign languages. Yet without technological support, mastering the 23 official languages of the member states of the European Union and some 60 other European languages is an insurmountable obstacle for the citizens of Europe and its economy, political debate, and scientific progress.

The solution is to build key enabling technologies. These will offer European actors tremendous advantages, not only within the common European market but also in trade relations with third countries, especially emerging economies. To achieve this goal and preserve Europe’s cultural and linguistic diversity, it is necessary to first carry out a systematic analysis of the linguistic particularities of all European languages, and the current state of language technology support for them. Language technology solutions will eventually serve as a unique bridge between Europe’s languages.

The automated translation and speech processing tools currently available on the market still fall short of this ambitious goal. The dominant actors in the field are primarily privately-owned for-profit enterprises based in Northern America. Already in the late 1970s, the EU realised the profound relevance of language technology as a driver of European unity, and began funding its first research projects, such as EUROTRA. At the same time, national projects were set up that generated valuable results but never led to concerted European action. In contrast to this highly selective funding effort, other multilingual societies such as India (22 official languages) and South Africa (11 official languages) have recently set up long-term national programmes for language research and technology development.

The predominant actors in LT today rely on imprecise statistical approaches that do not make use of deeper linguistic methods and knowledge. For example, sentences are automatically translated by comparing a new sentence against thousands of sentences previously translated by humans. The quality of the output largely depends on the amount and quality of the available sample corpus. While the automatic translation of simple sentences in languages with sufficient amounts of available text material can achieve useful results, such shallow statistical methods are doomed to fail in the case of languages with a much smaller body of sample material or in the case of sentences with complex structures.

The European Union has therefore decided to fund projects such as EuroMatrix and EuroMatrixPlus (since 2006) and iTranslate4 (since 2010), which carry out basic and applied research and generate resources for establishing high quality language technology solutions for all European languages. Analysing the deeper structural properties of languages is the only way forward if we want to build applications that perform well across the entire range of Europe’s languages.

European research in this area has already achieved a number of successes. For example, the translation services of the European Union now use MOSES open-source machine translation software that has been mainly developed through European research projects. A substantial breakthrough in the area of speech synthesis and recognition in Serbian was made by a group from the Faculty of Technical Sciences at the University of Novi Sad. Various applications in the fields of TTS and ASR have been developed based on the speech and lexical databases with accentuated word forms. Serbian speech recognition and generation has been commercialised by the AlfaNum company, a spin-off of the University of Novi Sad. The AlfaNum company has a considerable number of users among Serbian companies. The first corpus of contemporary Serbian, an electronic morphological dictionary of Serbian, aligned French-Serbian and English-Serbian corpora of literary texts, as well as different software tools were developed in the scope of joint projects of the Faculty of Mathematics and the Department of Serbian at the Faculty of Philology in Belgrade.

Drawing on the insights gained so far, it appears that today’s `hybrid' language technology mixing deep processing with statistical methods will be able to bridge the gap between all European languages and beyond. As this series of white papers shows, there is a dramatic difference between Europe's member states in terms of both the maturity of the research and in the state of readiness with respect to language solutions. Serbian is one of the ‘smaller’ European languages, and it needs further research before truly effective language technology solutions are ready for everyday use.

META-NET’s long-term goal is to introduce high-quality language technology for all languages in order to achieve political and economic unity through cultural diversity. The technology will help tear down existing barriers and build bridges between Europe’s languages. This requires all stakeholders – in politics, research, business, and society – to unite their efforts for the future.

This white paper series complements other strategic actions taken by META-NET (see the appendix for an overview). Up-to-date information such as the current version of the META-NET vision paper or the Strategic Research Agenda (SRA) can be found on the META-NET Website: http://www.meta-net.eu.