PyDataMTL

We ❤️ Data Science, Machine Learning, Deep Learning and meet once a month to learn from each other. Brought to you by @mariakhalusova and @alex000kim

[PyDataMTL @PyDataMTL]

Join us, we're live:

https://t.co/cUJyaOI2Ds

[PyDataMTL @PyDataMTL]

Our next meetup is dedicated to Data Engineering and Data Management. Join us on Friday, March 19th: https://t.co/DDWqk8enPu

[PyDataMTL @PyDataMTL]

If you missed our latest NLP meetup, don't worry, you can watch the recording of it whenever you have time :) https://t.co/YUaeZjRnh9

[PyDataMTL @PyDataMTL]

Join our meetup tomorrow, February 25th at 5:30 EST: https://t.co/upuOe7QANb
(5/5)

[PyDataMTL @PyDataMTL]

Finally, tomorrow we will learn from @TheShubhanshu. His talk is called "Understanding digital social trace data via Information Extraction"
Abstract:
I will describe how to efficiently extract information (e.g. phrases, named entities, and categories like topics, sentiment,(1/5)

[PyDataMTL @PyDataMTL]

I will end with ways on improving text classification via features derived from the DSTD representation. Details can be found at https://t.co/nPUwswUg3S. (4/5)

[PyDataMTL @PyDataMTL]

We will learn about the development process, deep dive into the code, and talk about applications. 3/3

Join the meetup: https://t.co/upuOe7yZoB

[PyDataMTL @PyDataMTL]

The second talk on the agenda of our upcoming NLP meetup is "Learning to translate with JoeyNMT" by @KreutzerJulia.
Abstract:
Machine translation is one of the most impactful NLP applications. Despite many toolkits for it being open-sourced, 1/3

[PyDataMTL @PyDataMTL]

we realized there was something missing: one that is developed for beginners and newcomers to the field. In this talk, we will get to know the JoeyNMT toolkit (https://t.co/R32uzj2daN), a minimalist toolkit for machine translation built on PyTorch. 2/3

[PyDataMTL @PyDataMTL]

@micbucci @jeremyphoward @GuggerSylvain Yes, there will be a recording.

[PyDataMTL @PyDataMTL]

The first talk of our next meetup: "Fine-tuning a large language model without your own supercomputer" by @GuggerSylvain
Abstract:
State-of-the-art results in NLP involve more and more the use of a generic pretrained language model fine-tuned on a specific downstream task. 1/4

[PyDataMTL @PyDataMTL]

5/4 https://t.co/upuOe7QANb

[PyDataMTL @PyDataMTL]

and show how to apply them on an example of fine-tuning. In particular, we will see how the variants of ZeRO are currently implemented in the Transformers library, by the use of fairscale and deepspeed. 4/4

[PyDataMTL @PyDataMTL]

This Thursday, February 25th, join us at 5:30 pm EST for an NLP-focused meetup with talks by @GuggerSylvain, @KreutzerJulia, and @TheShubhanshu https://t.co/upuOe7QANb

[Sylvain Gugger @GuggerSylvain]

I'll be talking at PyData Montreal at the end of the month about the recent additions to the Transformers library to fine-tune big models :-)

[Shubhanshu Mishra @TheShubhanshu]

Really excited to present some work from my PhD thesis (@iSchoolUI @DiesnerLab) on social media information extraction. Also, looking forward to the talks of @GuggerSylvain and @KreutzerJulia

More details:
SocialMediaIE: https://t.co/8ugLNVyQcm
Thesis: https://t.co/YyOYMXJS6b