
Join us, we're live: youtube.com/watch?v=NrdJOfYi…

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

Join us, we're live: youtube.com/watch?v=NrdJOfYi…

Our next meetup is dedicated to Data Engineering and Data Management. Join us on Friday, March 19th: meetup.com/PyData-MTL/events…

If you missed our latest NLP meetup, don't worry, you can watch the recording of it whenever you have time :) youtube.com/watch?v=RG-yV5zg…

Join our meetup tomorrow, February 25th at 5:30 EST: meetup.com/PyData-MTL/events… (5/5)

I will end with ways on improving text classification via features derived from the DSTD representation. Details can be found at shubhanshu.com/phd_thesis/. (4/5)

Next, I will show how information extraction from social media data can be looked through the lens of an abstraction called digital social trace data (DSTD) which allows us to utilize the graph structure of the data for developing new information extraction tasks. (3/5)

sarcasm, or abuse) from social media text using semi-supervised, multi-task, and active learning to more accurately identify phrases, named entities, and classification. I will introduce an open source tool called SocialMediaIE. (2/5)

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)

We will learn about the development process, deep dive into the code, and talk about applications. 3/3 Join the meetup: meetup.com/PyData-MTL/events…

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 (github.com/joeynmt), a minimalist toolkit for machine translation built on PyTorch. 2/3

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


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

In this talk, we will dive into the techniques one can use to reduce the GPU-memory used when fine-tuning a model (gradient accumulation, gradient checkpointing, model parallelism, and the more recent ZeRO/ZeRO-offload developments), 3/4

This, in turn, has led researchers to develop larger and larger language models, which give better results than their smaller versions but can be hard to use without powerful (and expensive) hardware. 2/4

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