Segmentation and Tagging - multi-objective

This is a partial release of Deeplima models, including segmentation and tagging models, as well as a few lemmatization models.
These models have been trained with a multi-objective optimization strategy. The best ones for tokens, upos and lemmas have been selected.

Tagging models

v0.1.6-beta-morph

Update README.md

Embeddings for English (1/10 of C4)

v0.1.6-beta-en-c4medium

Update README.md

Tokenization models

Tokenization only (without sentence segmentation) models trained on all trainable corpora from UD 2.8 collection (67 languages), 8 models for each corpus.
Deeplima commit: aymara/lima@40ab9ad
LSTM hidden state: 8

v0.1.5

• lemmatization models updated
• speed improved
• Albanian language added

Models for 60+ languages

v0.1.4-beta

Fix path to copyright

MorphoSyntax models for English and French

Starting from this version models are packaged per language.

v0.1.2-beta

Models are installed to /usr/.

Tokenization models for English

v0.1.1-beta

English tokenization models