Introducing the Digital Language Equality Metric: Contextual Factors
In our digital age, digital language equality is an important goal to enable participation in society for all citizens, independent of the language they speak. To assess the current state of play with regard to Europe’s languages, we developed, in the project European Language Equality, a metric for digital language equality that consists of two parts, technological and contextual (i.e., non-technological) factors. We present a metric for calculating the contextual factors for over 80 European languages. For each language, a score is calculated that reflects the broader context or socio-economic ecosystem of a language, which has, for a given language, a direct impact for technology and resource development; it is important to note, though, that Language Technologies and Resources related aspects are reflected by the technological factors. To reduce the vast number of potential contextual factors to an adequate number, five different configurations were calculated and evaluated with a panel of experts. The best results were achieved by a configuration in which 12 manually curated factors were included. In the factor selection process, attention was paid to data quality, automatic updatability, inclusion of data from different domains, and a balance between different data types. The evaluation shows that this specific configuration is stable for the official EU languages; while for regional and minority languages, as well as national non-official EU languages, there is room for improvement.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Introducing the Digital Language Equality Metric: Technological Factors
This paper introduces the concept of Digital Language Equality (DLE) developed by the EU-funded European Language Equality (ELE) project, and describes the associated DLE Metric with a focus on its technological factors …
Overview of the ELE Project
This paper provides an overview of the ongoing European Language Equality(ELE) project, an 18-month action funded by the European Commission which involves 52 partners. The primary goal of ELE is to prepare the European …
Collaborative Metadata Aggregation and Curation in Support of Digital Language Equality Monitoring
The European Language Equality (ELE) project develops a strategic research, innovation and implementation agenda (SRIA) and a roadmap for achieving full digital language equality in Europe by 2030. Key component of the S…
Sparse Additive Contextual Bandits: A Nonparametric Approach for Online Decision-making with High-dimensional Covariates
Personalized services are central to today's digital landscape, where online decision-making is commonly formulated as contextual bandit problems. Two key challenges emerge in modern applications: high-dimensional covari…
Decision MakingMulti-Armed BanditsThe production of meaning in the processing of natural language
Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions. Experiment…
Natural Language Understanding