Q: Why build an in-house #NER engine, in 2021? Why not use #opensource?
A: Performance + accuracy + flexibility. Definitely worth it 👌 (if you know what you're doing)
#SmartOpen release 1.8.1 out! Improved streaming of large data:
✓ added streaming from HTTP, SSH/SCP/SFTP
✓ compressor registry for streaming from compressed files
✓ improved testing and compatibility
https://t.co/YoibSPBQRP
✍ Automatically extracting hand-printed fields from scanned documents with #DeepLearning.
Our new case study with AXA Insurance: https://t.co/RLiijVvWoq
Getting ready to fly to London for @DataProtectWF tomorrow! Presenting https://t.co/zaRCTZBHWM at booth #10, come & test drive our new gen of #dataprivacy + #ML 🤖
@alvations Chapter 11 did not inspire #Bounter (we didn't know about it), but I'm sure there's interesting information in it :-) @ianozsvald@gensim_py
https://t.co/myIQbYACPy
"Advances in Semantic Textual Similarity": @GoogleAI's new post on universal text embeddings: https://t.co/Xk2vyZTndj
Pre-trained 512 dim #Tensorflow model: https://t.co/6FOngCGXHm (already available in @scaletext_ai)
@icoxfog417@gensim_py@unnonouno@menshikh_iv Blood, sweat and tears!
#Gensim costs us money; same for #sklearn etc. Not cheap to maintain quality OSS. Think ahead and either plan to embed your OSS commercially (offer services, trainings, products), or rely on grants/subsidies/donations. But don't hope for miracles.
🔥 Come join our #Gensim team at @MLPrague next Friday! We'll run a workshop on unsupervised topic modeling and practical neural network embeddings (#word2vec, #fasttext): https://t.co/N7KeJeDdSr
🔥 Come join our #Gensim team at @MLPrague next Friday! We'll run a workshop on unsupervised topic modeling and practical neural network embeddings (#word2vec, #fasttext): https://t.co/N7KeJeDdSr
Our instructors @kjam@pmigdal delivering hands-on #ML & #NLProc workshop for Aon Dublin @ACIA_ie. Great team!
See our courses https://t.co/3asJsyQWcx
In case you missed our cloud #GPU benchmarks, pretrained #NLP models, Count-min Sketch tutorial, Poincare Embeddings, #gsoc2018 & more. https://t.co/QZZt5NX4Ra