no code implementations • 7 Nov 2018 • Gregor Wiedemann, Raghav Jindal, Chris Biemann
We evaluate the performance of different word and character embeddings on two standard German datasets and with a special focus on out-of-vocabulary words.
no code implementations • 7 Nov 2018 • Gregor Wiedemann, Eugen Ruppert, Raghav Jindal, Chris Biemann
Best results are achieved from pre-training our model on the unsupervised topic clustering of tweets in combination with thematic user cluster information.