NLP IL 7th Meetup - Tal Geva and Amir David Nissan Cohen

We are pleased to announce our next Meetup, featuring amazing talks on Hebrew NLP and relations extraction performance.

Agenda (Sunday, August 15th):

19:30 - 19:35 - Quick introduction

19:35-20:20 - Amir David Nissan Cohen, a PhD candidate at Bar Ilan University.
*Questions based models for SOTA relation extraction performance *

Most of the current supervised relation classification (RC) algorithms use a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as a Span-Prediction (SP) problem, similar to Question Answering (QA). We present an SP-based system for RC and evaluate its performance compared to the embedding-based system. We demonstrate that by adding a few improvements, the supervised SP objective works significantly better than the standard classification-based objective. We achieve state-of-the-art results on the canonical RC datasets. This approach was also shown to provide excellent cross-relation type transfer learning results.

20:20 -21:10 - Tal Geva, HEB +Arab NLP national program manager

What do we need for really good Hebrew NLP?
The Israeli government is initiating a program designed to improve NLP capabilities. What's in it for me?

You are all invited to join the NLP IL community at:
Facebook: bit.ly/nlp-il
LinkedIn: bit.ly/nlp_il_linkedin
Talk Proposal Form: bit.ly/nlp-il-talk
YouTube Channel: bit.ly/nlp_il_youtube