TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Do, Bich-Ngoc
A1  - Rehbein, Ines
A1  - Frank, Anette
T1  - What do we need to know about an unknown word when parsing German
T2  - Proceedings of the First Workshop on Subword and Character Level Models in NLP (EMNLP 2017). September 7, 2017 Copenhagen, Denmark
N2  - 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.
KW  - Deutsch
KW  - Kompositum
KW  - Automatische Spracherkennung
KW  - part-of-speech (POS)
Y1  - 2017
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-80244
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-80244
UR  - http://www.aclweb.org/anthology/W17-4117
UR  - https://aclanthology.info/papers/W17-4100/w17-4100
SN  - 978-1-945626-91-3
SB  - 978-1-945626-91-3
SP  - 117
EP  - 123
PB  - The Association for Computational Linguistics
CY  - Stroudsburg PA, USA
ER  -