Refine
Year of publication
- 2017 (2) (remove)
Document Type
- Part of a Book (1)
- Conference Proceeding (1)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2) (remove)
Keywords
- Betrieb (1)
- Bildung (1)
- Computerlinguistik (1)
- Deep learning (1)
- Deutsch (1)
- Estland (1)
- Estonia (1)
- German (1)
- Maschinelles Lernen (1)
- Muttersprache (1)
Publicationstate
- Postprint (2)
- Zweitveröffentlichung (2)
Reviewstate
- (Verlags)-Lektorat (1)
- Peer-Review (1)
Publisher
- Springer (2) (remove)
This chapter investigates policies which shape the role of the German language in contemporary Estonia. Whereas German played for many centuries an important role as the language of the economic and cultural elite in Estonia, it severely declined in importance throughout the twentieth century. Mirrored on this historical background, the paper provides an overview of the current functions of German and attitudes towards it and it discusses how these functions and attitudes are influenced by policies of various actors from inside and outside Estonia. The paper argues that German continues to play a significant role: while German is no longer a lingua franca, it still enjoys a number of functions and prestige in clearly defined niches involving communication within German-speaking circles or between Estonians and Germans. The interplay of language policies of the Estonian and the German-speaking states as well as by semi-state and private institutions succeed in maintaining German as an additional language in contemporary Estonia.
We present a supervised machine learning AND system which tackles semantic similarity between publication titles by means of word embeddings. Word embeddings are integrated as external components, which keeps the model small and efficient, while allowing for easy extensibility and domain adaptation. Initial experiments show that word embeddings can improve the Recall and F score of the binary classification sub-task of AND. Results for the clustering sub-task are less clear, but also promising and overall show the feasibility of the approach.