nlptown

Natural Language Processing Consultancy and Development. Makers of

[nlptown @nlptown]

Can you do text classification without any labeled training examples? We put the zero-shot #classification pipelines in @huggingface Transformers and Flair to the test, and wrote up our findings: https://t.co/mIpc4TkyEv

#nlp #nlproc #deeplearning #artificialintelligence #ai

[nlptown @nlptown]

What #nlproc models work best for the identification of organizations in English #financial news? @stanfordnlp Stanza's BiLSTM-CRF comfortably beats @spacy_io's CNN-based models, but can't compete with spaCy's transformer-based pipeline. #deeplearning #AI #machinelearning

[nlptown @nlptown]

We evaluated @spacy_io's entity recognition on 14 days of English #financial news. The non-neural models all struggle with the identification of organizations, but look how the transformer pipeline shines! 🤯 #nlproc #deeplearning

Labeling with https://t.co/JfAQjEedly

[nlptown @nlptown]

#NLProc data #annotation is a team effort. The latest version of our labeling tool #Tagalog allows project managers to organize labeling campaigns and track the progress of annotators and reviewers in real time. https://t.co/JfAQjEedly #ai #machinelearning #artificialintelligence

[nlptown @nlptown]

@TDehaene Thanks, @TDehaene! We support both use cases. Most clients use our central hosting, but some prefer a local deployment for their projects — because of privacy or other reasons.

[nlptown @nlptown]

Many #ai and #machinelearning projects fail because of low-quality labeled #data. For challenging #annotation tasks, it's crucial to have several annotators label the documents and review the conflicts. Our labeling tool #Tagalog is there to support you in those projects. #nlproc

[nlptown @nlptown]

We've given our data #labeling tool a revamp, as well as a new name: Tagalog. Get in touch if you're struggling with an #annotation project and need help. #machinelearning #datascience #textmining #nlproc

[nlptown @nlptown]

@jganseman Hoi Joachim, dat zou je met https://t.co/6KqIYFHe7W moeten bespreken.

[nlptown @nlptown]

Today we're taking @spacy_io v3 for a spin in a project on grammar correction. ✍️ Loving the config-based training and the integration with @wandb. 😍 Also, these #transformers look pretty promising. 🧐 Are they a thing? 😏 @honnibal @_inesmontani @OxyKodit #NLProc

[nlptown @nlptown]

😍 We're simply in awe at @spacy_io's v3.0 release. So many new features will have an immediate impact on our projects: transformer pipelines, the new workflow system, etc. Kudos to @honnibal, @_inesmontani and @OxyKodit!

https://t.co/9kbE0AocD1 #nlproc #deeplearning #ai

[nlptown @nlptown]

We thought that #deeplearning in #nlproc had reached peak hype with #BERT, but that was nothing compared to @OpenAI's #GPT3. Just about every client thinks their problem is solved now. #AI

[nlptown @nlptown]

Today we were experimenting with @GoogleTranslatr glossaries. We were expecting some nifty #deeplearning solution, but instead it just appears to replace words blindly, with agreement and other grammatical errors as a result. Can't @GoogleAI do better? #neuralempty #nlproc

[nlptown @nlptown]

Data #annotation and quality is critical in #ArtificialIntelligence and #NLProc. That's why we developed #Taggle, a state-of-the-art labeling platform for all your text annotation projects. Take a look at https://t.co/FI1bWRgeJU to find out more.

[nlptown @nlptown]

@huggingface @ClementDelangue @Thom_Wolf No worries, thanks for the quick solution!

[nlptown @nlptown]

Hey @huggingface, it looks like the model card for our finetuned sentiment model is down. It worked perfectly a few weeks ago, including the inference widget. Anything we can do to fix this? @ClementDelangue @Thom_Wolf

[nlptown @nlptown]

@huggingface @ClementDelangue @Thom_Wolf Thank you!

[nlptown @nlptown]

We're loving the inference widget in v2 of the @huggingface model hub, which lets you try out all shared #nlproc models, including our 6-language #SentimentAnalysis model. Also great to see our model has been downloaded almost 64,000 times in the past 30 days! #deeplearning #ai

[nlptown @nlptown]

Our #Python #NLProc Toolbox for 2019 has some shiny newcomers (@huggingface's Transformers, @streamlit, @tiangolo's FastAPI), rising stars (@Rasa_HQ and @ZalandoTech's Flair) and of course the usual suspects (@spacy_io). Let us know what you think! #machinelearning #deeplearning

[nlptown @nlptown]

Evaluation and communication are central to the development of successful AI software. At NLP Town, we've recently started using @streamlit to experiment with our machine learning models and share the results with our clients. #nlproc #ArtificialIntelligence #machinelearning

[nlptown @nlptown]

We're still excited by the great turnout and interesting talks at yesterday's 12th Belgium NLP Meetup. We hope to see you all again for the next meetup in early 2020! #nlproc #ai #deeplearning #ArtificialIntelligence #textmining #metup