AI in Action Virtual Meetup: NLP Series #2

Join us on Wednesday 19th of August from 4pm GMT as we bring you the second of our NLP focused AI in Action Virtual Meetup.

SPEAKERS

1. Thomas Vrancken, ML Engineer at ML6.

Title: It's alive! Designing and improving real-world NLP for production systems.

This talk will share some insights they obtained during the development and go-live of a recent NLP-powered client application. What worked and what didn't? The application in question is a search engine based on document embeddings. He will discuss how to host their ML models on google cloud, integrating the search engine with elasticsearch, and how they use kubeflow pipelines to automate their workflows.

2. Procheta Sen, PhD Student at ADAPT Centre DCU

Title: Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning

The prevalent existence of cognitive biases in large volumes of historical data can pose a threat of being manifested as unethical and seemingly inhumane predictions as outputs of AI systems trained on such data. To alleviate this problem, Procheta and her team propose a bias-aware multi-objective learning framework that given a set of identity attributes (e.g. gender, ethnicity etc.) and a subset of sensitive categories of the possible classes of prediction outputs, learns to reduce the frequency of predicting certain combinations of them.

3. Alexander O'Connor, Lead Data Scientist at Autodesk

Title: Recent trends in NLP - An Industry Perspective

Transformers have been the dominant technology in natural language processing for more than a year now. The most exciting thing is that technology is growing capability month by month. This astonishing progress, along with unprecedented availability of code and data, make it a compelling tool for industrial applications. This talk covers some experience of using Transformers in industry, as well as some of the recent exciting trends in the area.