Textacy

Textacy bietet (fast) alle NLP-Vorbereitungsaufgaben in einem Paket:

https://chartbeat-labs.github.io/textacy/

Textacy basiert auf SpaCy: https://spacy.io

Installieren:

• CPPFLAGS="-std=c++98" pip install --upgrade --user 'textacy[lang]'
• Modelle installieren: python3 -m spacy download en (oder statt en andere Sprachen)

nutzen:

• import textacy
• doc = textacy.Doc(text)
• doc.pos_tagged_text[0]

etc. Mehr Doku ist oben verlinkt.

quick-nlp

https://github.com/outcastofmusic/quick-nlp

Beschreibung von der Website:

Quick NLP is a deep learning nlp library inspired by the fast.ai library

Can run a seq2seq model with a few lines of code similar to existing fast.ai examples Easy to expand/train and try different models or use different data

Ready made algorithms to try out

• Seq2Seq https://arxiv.org/abs/1506.05869
• Seq2Seq with Attention https://arxiv.org/abs/1703.03906
• HRED http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14567/14219
• Attention is all you need (In Progress) http://papers.nips.cc/paper/7181-attention-is-all-you-need
• Depthwise Separable Convolutions for Neural Machine Translation (TODO) https://arxiv.org/abs/1706.03059

-- ArneKoehn - 12 Apr 2018