What do we need to know about an unknown word when parsing German

Bich-Ngoc Do, Ines Rehbein, Anette Frank


Abstract
We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German. We present an extrinsic evaluation where we use the compound embeddings as input to a neural dependency parser and compare the results to the ones obtained with other types of embeddings. Our evaluation shows that adding compound embeddings yields a significant improvement of 2% LAS over using word embeddings when no POS information is available. When adding POS embeddings to the input, however, the effect levels out. This suggests that it is not the missing information about the semantics of the unknown words that causes problems for parsing German, but the lack of morphological information for unknown words. To augment our evaluation, we also test the new embeddings in a language modelling task that requires both syntactic and semantic information.
Anthology ID:
W17-4117
Volume:
Proceedings of the First Workshop on Subword and Character Level Models in NLP
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venues:
SCLeM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
117–123
Language:
URL:
https://www.aclweb.org/anthology/W17-4117
DOI:
10.18653/v1/W17-4117
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-4117.pdf