Lecture:

HIDA Lectures @ HEIBRiDS

Tuesday, 15.06.2021 · 16:00
Online

Helmholtz Information & Data Science Academy Lectures

The HIDA Lectures are a series of events organized by HIDA together with the six Helmholtz Information & Data Science Schools. Throughout the year, the Data Science Schools invite outstanding international Data Scientists to speak about their current research.

As the Schools represent all Helmholtz research areas - Energy; Earth and Environment; Health; Information; Matter; and Aeronautics, Space and Transport - the series will reflect a broad range of topics and offers a great opportunity to dive into the diversity of current approaches in Data Science.

We cordially invite the interested public and especially PhD students of the Helmholtz Association. You will get an insight into the diverse activities of the Schools and HIDA, but above all you will be able to discuss with international researchers about different application fields of Data Science.

All events in the series are open to the public.

This HIDA Lecture is hosted by the Helmholtz Einstein International Berlin Research School in Data Science HEIBRiDS.

HIDA Lectures@HEIBRiDS

Date: June 16, 2021, 4 p.m.

Title: "TARS: Few-Shot Learning for Natural Language Processing" (Lecture language English)

Speaker: Alan Akbik, Humboldt University of Berlin

Abstract: Machine learning models for natural language processing (NLP) are typically trained with very large amounts of labeled training data. However, such data is often not readily available and very expensive to produce. In this talk, I introduce TARS, a novel approach in the research area of few-shot learning that allows us to train text classification models with very little training data - or even none at all! I show how the proposed approach can be applied to a continuous learning setup, where a single model learns a set of different tasks sequentially, with the goal of learning all tasks. Finally, I give a brief overview of the Flair NLP framework that we are developing in my group together with the open source community, and show how you can use TARS (and other NLP components in Flair) in your own research or industry projects.

More information about the HEIBRiDS Lecture Series

Do you want to see Alan Akbik's lecture?

To the video

Alternativ-Text

Subscribe newsletter