TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Müller, Mark-Christoph
A1  - Strube, Michael
ED  - Zhao, Dongyan
T1  - Transparent, efficient, and robust word embedding access with WOMBAT
T2  - Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations. August 20-26, 2018, Santa Fe, New Mexico, USA
N2  - We present WOMBAT, a Python tool which supports NLP practitioners in accessing word embeddings from code. WOMBAT addresses common research problems, including unified access, scaling, and robust and reproducible preprocessing. Code that uses WOMBAT for accessing word embeddings is not only cleaner, more readable, and easier to reuse, but also much more efficient than code using standard in-memory methods: a Python script using WOMBAT for evaluating seven large word embedding collections (8.7M embedding vectors in total) on a simple SemEval sentence similarity task involving 250 raw sentence pairs completes in under ten seconds end-to-end on a standard notebook computer.
KW  - Python <Programmiersprache>
KW  - Automatische Sprachanalyse
KW  - Code
KW  - Computerlinguistik
KW  - word embedding
KW  - WOrd eMBedding dATabase (WOMBAT)
Y1  - 2018
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-110862
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-110862
UR  - https://aclanthology.org/C18-2012
SN  - 978-1-948087-53-7
SB  - 978-1-948087-53-7
SP  - 53
EP  - 57
PB  - Association for Computational Linguistics
CY  - Stroudsburg, Pennsylvania
ER  -