Ethics in NLP & A Practical Introduction to Image Retrieval
Details
On December 1st at 7pm, we will meet online for our last meetup event of the year! 🎉 The first talk is about "Ethics in Natural Language Processing", where Marty Oelschläger from dida Datenschmiede revisits discussions around the ethical implications of large NLP models, how to use them responsibly, and how to mitigate their inherent biases and stereotypes. With the second talk, "A Practical Introduction to Image Retrieval" by Sara Zanzottera from deepset, we look into NLP beyond text data and learn how semantic search engines can retrieve relevant images based on text queries. Here are the detailed talk descriptions:
Ethics in Natural Language Processing
by Marty Oelschläger from dida Datenschmiede
In recent years, we have seen a wave of large (to enormously large) NLP models trained on massive amounts of mostly uncurated data. While the models draw the information on how to correctly use words and their relationships to each other in various different languages, the data - and thus the models - also contain biases and stereotypes. Most of the groups against which these biases and stereotypes are directed do not belong to the part of the population that particularly benefits from the developments in NLP. In this talk, we want to revisit discussions around the ethical implications of large language models and how to use them responsibly.
A Practical Introduction to Image Retrieval
by Sara Zanzoterra from deepset
Search should not be limited to text only. Recently, Transformers-based NLP models started crossing the boundaries of text data and exploring the possibilities of other modalities, like tabular data, images, audio files, and more. Text-to-text generation models like GPT now have their counterparts in text-to-image models, like Stable Diffusion. But what about search? In this talk we're going to experiment with CLIP, a text-to-image search model, to look for animals matching specific characteristics in a dataset of pictures. Does CLIP know which one is "The fastest animal in the world"?
As always, we will have small breakout room sessions after the talks to connect and discuss. If you would like to join us, make sure to RSVP on the event page. You can find the Zoom link there as well. Looking forward to meeting you online in four weeks!
PS: For those of you who'd like to do some light reading about NLP, you can get some good resources built by deepset for NLP practitioners and project managers here:
Ethics in NLP & A Practical Introduction to Image Retrieval