@inproceedings{HorchReich2016,
title = {On “Article Omission” in German and the “Uniform Information Density Hypothesis”},
author = {Ingo Reich and Eva Horch},
editor = {Stefanie Dipper and Friedrich Neubarth and Heike Zinsmeister},
url = {https://www.linguistics.rub.de/konvens16/pub/16_konvensproc.pdf},
year = {2016},
date = {2016},
booktitle = {Proceedings of the 13th Conference on Natural Language Processing (KONVENS 2016)},
pages = {125-127},
address = {Bochum},
abstract = {This paper investigates whether Information Theory (IT) in the tradition of Shannon (1948) and in particular the “Uniform Information Density Hypothesis” (UID, see Jager 2010) might contribute to our understanding of a phenomenon called “article omission” (AO) in the literature. To this effect, we trained language models on a corpus of 17 different text types (from prototypically written text types like legal texts to prototypically spoken text types like dialogue) with about 2.000 sentences each and compared the density profiles of minimal pairs. Our results suggest, firstly, that an overtly realized article significantly reduces the surprisal on the following head noun (as was to be expected). It also shows, however, that omitting the article results in a non-uniform distribution (thus contradicting the UID). Since empirically AO seems not to depend on specific lexical items, we also trained our language models on a more abstract level (part of speech). With respect to this level of analysis we were able to show that, again, an overtly realized article significantly reduces the surprisal on the following head noun, but at the same time AO results in a more uniform distribution of information. In the case of AO the UID thus seems to operate on the level of POS rather than on the lexical level.},
pubstate = {published},
type = {inproceedings}
}