German in Flux: Detecting Metaphoric Change via Word Entropy

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 354–367, Vancouver, Canada, August 3 - August 4, 2017. c⃝2017 Association for Computational Linguistics German in Flux: Detecting Metaphoric Change via Word Entropy Dominik Schlechtweg∗†, Stefanie Eckmann‡, Enrico Santus3, Sabine Schulte im Walde∗, Daniel Hole† ∗Inst. for Natural Language Processing, University of Stuttgart, Germany †Dept. of Linguistics/German Studies, University of Stuttgart, Germany ‡Historical and Indo-European Linguistics, LMU Munich, Germany 3Singapore University of Technology and Design, Singapore dominik.schlechtweg@gmx.de, stefanie.eckmann@campus.lmu.de, esantus@mit.edu, schulte@ims.uni-stuttgart.de, holedan@gmail.com Abstract This paper explores the information- theoretic measure entropy to detect metaphoric change, transferring ideas from hypernym detection to research on language change. We also build the first diachronic test set for German as a standard for metaphoric change annota- istion. Our model shows high performance, unsupervised, language-independent and generalizable to other processes of semantic change. 1 Introduction Recently, computational linguistics has shown an increasing interest in language change. This inter- est is focused on making semantic change mea- surable. However, even though different types of semantic change are well-known in historical linguistics, little effort has been made to distin- guish between them. A very basic distinction in historical linguistics is the one between inno- vative meaning change (also polysemization)— e.g., German br¨uten ‘breed’ > ‘breed, brood over sth.’—and reductive meaning change—e.g., Ger- man schinden ‘to skin, torture’ > ‘to torture’ (cf. Koch, 2016, p. 24–27). Metaphoric mean- ing change is an important sub-process of inno- vative meaning change. Hence, a computational model of semantic change should be able to dis- tinguish metaphoric change from other—typically less strong—types of change. Such a model, particularly if applicable to different languages, would be beneficial for a number of areas: (i), his- torical linguists may test their theoretical claims about semantic change on a large-scale empirical basis going beyond the traditional corpus-based approaches; (ii), linguists and psychologists work- ing on metaphor in language or cognition may benefit by gaining new insights into the diachronic aspects of metaphor which are not yet as central in these fields as the synchronic aspects; and, fi- nally, (iii), the Natural Language Processing re- search community may benefit by applying the model presented here to a wide range of tasks in which polysemy and non-literalness are involved. Our aim is to build an unsupervised and language-independent computational model which is able to distinguish metaphoric change from semantic stability. We apply entropy (a measure of uncertainty inherited from informa- tion theory) to a Distributional Semantic Model (DSM). In particular, we exploit the idea of se- mantic generality applied in hypernym detection, to detect metaphoric change as a special process of meaning innovation. German will serve as a sample language, since there is a rich historical corpus available covering a large time period. Nevertheless, our model is presumably applicable to other languages requiring only minor adjust- ments. With the model, we introduce the first resource for evaluation of models of metaphoric change and propose a structured annotation pro- cess that is generalizable to the creation of …

Content truncated to 500 words