A Sustainable and Open Access Knowledge Organization Model to Preserve Cultural Heritage and Language Diversity

Abstract

This paper proposes a new collaborative and inclusive model for Knowledge Organization Systems (KOS) for sustaining cultural heritage and language diversity. It is based on contributions of end-users as well as scientific and scholarly communities from across borders, languages, nations, continents, and disciplines. It consists in collecting knowledge about all worldwide translations of one original work and sharing that data through a digital and interactive global knowledge map. Collected translations are processed in order to build multilingual parallel corpora for a large number of under-resourced languages as well as to highlight the transnational circulation of knowledge. Building such corpora is vital in preserving and expanding linguistic and traditional diversity. Our first experiment was conducted on the world-famous and well-traveled American novel Adventures of Huckleberry Finn by the American author Mark Twain. This paper reports on 10 parallel corpora that are now sentence-aligned pairs of English with Basque (an European under-resourced language), Bulgarian, Dutch, Finnish, German, Hungarian, Polish, Portuguese, Russian, and Ukrainian, processed out of 30 collected translations.

The Landscapes of Sustainability in the Library and Information Science: Systematic Literature Review

“…Over 30 translations were obtained, and on the base of their content, 10 parallel corpora were built. The authors reported further that during the process, 22 under-represented languages were identified amongst all gathered full-text translations [60], which is a sign of the impressive scale of response from end-users, and of a promising potential for the future of this project.…”

“…Fraisse et al [60] express their conviction that language is one of the most important barriers that pose an obstacle to the sustaining of global knowledge diversity. The authors indicate that a number of efforts that have been taken by the LIS community, e.g., KOS' development, making progress in the IRs discipline, outworking of metadata exchanging standards, and multilingual electronic libraries and archival projects, all help to create efficient, cheap, and reliable resources for the purpose of preserving rare or expiring languages [60]. Apart from that, they claim that the language barrier is also a central issue, which has to be addressed by International Society for Knowledge Organization (ISKO) authorities.…”

“…This is the reason the group of authors decided to present a new paradigm, which is designed for the community of volunteers, who are willing to take part in the knowledge organization process. Being more precise, the idea is about engaging as many widespread contributors as possible, who would add their unique parts of knowledge about translations of some noteworthy original works written in underrepresented languages [60]. The authors actually conducted an experiment in this area, and their choice fell to the famous novel "Adventures of Huckleberry Finn".…”

Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models

“…In a case study of comparing human and machine translations, Ahrenberg (2017) suggested that the human translator used several procedures that seem to be beyond the reach of the MT system (such as sentence splitting, shifts of phrase function and/or category, explicitation, modulation and paraphrasing). The project of Fraisse et al (2019) aims to preserve cultural heritage and language diversity by analyzing the translation adaptations in multilingual corpora of translated literary texts, which is particularly important for low-resource languages. In order to provide insights for discourse-aware MT system's development, discourse-related language contrasts are analyzed for English-Croatian and English-German (Lapshinova-Koltunski and Hardmeier, 2017;Šoštarić et al, 2018).…”

Towards Language Service Creation and Customization for Low-Resource Languages

“…Some studies use crowdsourcing approaches to annotate lexicons [20] and collect speech recognition data [21] for low-resource languages. Some other research proposes a collaborative model for different types of volunteers and contributors to take part in the knowledge organization process for sustainable preservation of language diversity and succeeds in building multilingual parallel corpora for low-resource languages [22,23]. However, it is always time consuming and costly to create resources and NLP tools for low-resource languages when starting from scratch.…”