Alexander Panchenko

For models trained on a big corpus, like 60 Gb of text calculation of NNs is terribly long. Like 50-100 NNs per hour for this model: http://panchenko.me/data/joint/adagram/clean_lemma_model_alpha_05 Any possibility to...

In the new interface, it would be great to have a reduced font size in the title (the URL of the retrieved document).

Construct entity sense embeddings using DT and DeepWalk

15

Background ===== - Sense Embeddings: https://arxiv.org/pdf/1805.04032.pdf - Our sense embedding approach: http://aclweb.org/anthology/W16-1620 Data ==== 1. A Distributional Thesaurus (DT) - http://panchenko.me/data/joint/dt/common-crawl-2016/ - panchenko@ltdata1:/srv/data/depcc/distributional-models - use the model 1000-2000: http://panchenko.me/data/joint/dt/common-crawl-2016/dependency_lemz-true_cooc-false_mxln-110_semf-true_sign-LMI_wpf-1000_fpw-2000_minw-5_minf-5_minwf-2_minsign-0.0_nnn-200/SimPruned/ -...