Times are given in Irish Standard Time (IST), i.e., either UTC+0 or UTC+1 (Daylight Saving).
- This event has passed.
Cardamom Seminar Series #6 – Nils Reimers (Hugging Face)
October 26 @ 5:00 pm – 6:00 pm IST
The Unit for Linguistic Data at the Insight SFI Research Centre for Data Analytics / Data Science Institute, National University of Ireland Galway is delighted to welcome Nils Reimers, research scientist at Hugging Face, to be the next speaker in our seminar series. He will talk about his research on the application of neural networks in low resource settings. Register here.
Search results can be significantly improved by using neural networks; however, those models are often fine-tuned on hundred thousands of annotated data pairs. For many cases and languages other than English, such large labelled datasets are sadly seldom available. This talk will cover different approaches and how to train these methods if no or only little labelled data is available.
About the Speaker:
Nils Reimers holds the position of Research Scientist at Hugging Face. He is not only an NLP scientist but a professional web developer. He is also interested in entrepreneurship and especially interested in IT start-ups that use bleeding-edge technology.
Dr Reimers is an expert in Natural Language Processing with a particular focus on deep learning. His main research interest is in representing the semantics of words, sentences, and paragraphs in vector spaces such that texts with similar meanings are close. He has also developed state-of-the-art open-source solutions commonly known as Sentence BERT (SBERT), which are very popular in research & industry.
The seminar series is led by the Cardamom project team. The Cardamom project aims to close the resource gap for minority and under-resourced languages using deep-learning-based natural language processing (NLP) and exploiting similarities of closely related languages. The project further extends this idea to historical languages, which can be considered closely related to their modern form. It aims to provide NLP through both space and time for languages that current approaches have ignored.