PyData Edinburgh - Extracting Entity-Relation Triples from Text
Description changed:
Details
Welcome to the fourth meetup for the PyData Edinburgh group! We will be at Wood Mackenzie once again this month and look forward to meet you all!
The format will be the usual: a main talk and lightning ones following. Lightning talks are an opportunity for everyone to speak, in strictly 5 minutes, about something of interest: they don't need to be communicated in advance and you can sign up on the day. They have been quite successful in the last events so please feel free to do one!
TALK DETAILS
=============
TITLE: Extracting Entity-Relation Triples from Text
---------------------------------------------------------------------------
Presenter: Liane Guillou
Liane is a researcher at the University of Edinburgh, working on entity-relation extraction and discourse in machine translation. She has a PhD in Natural Language Processing from the University of Edinburgh. She has also worked for an Edinburgh-based start up, and as a developer and database administrator in the financial sector.
Description:
Liane will present her work on automatically extracting entity-relation triples from German text using a Python-based pipeline. Possible downstream applications of this work include question answering, fact checking, and semantically informed machine translation. The talk will cover the basic components of the pipeline and the underlying Natural Language Processing concepts, including tokenisation, parsing, named entity recognition, and how these steps combine in the extraction of entity-relation triples.
LIGHTNING TALKS
==================
Share your stories! Share your successes & failures! Share your hints & tips! Whether you are a beginner or an expert, we want to hear from you.
Lightning talks have been really popular at other PyData meetups, so let's get the ideas flowing in Edinburgh!
No need for slides (bring them on a memory stick if you do have some though) and no need to be an expert speaker!
Just sign up on the evening: anything goes (within reason!) and no more than 5 minutes long — we'll be bringing the alarm clock!
LOGISTICS
===========
We've kindly been invited to use the great facilities at Wood Mackenzie— please note all attendees MUST sign up to the Meetup to be admitted.
Doors open at 1815 with refreshments.
Talks kick off with an update on news relating to the PyData community at 1845.
And we'll end the evening with pizza and more refreshments, wrapping up by 2100.
SPONSORS & REFRESHMENTS
=============================
As always, we couldn't do this without our sponsors help to provide a venue and drink & pizzas — Cathcart Associates (https://www.cathcartassociates.com), Wood Mackenzie (https://www.woodmac.com) and Canon Medical (https://research.eu.medical.canon)
CODE OF CONDUCT
====================
The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen (+1 512-222-5449; leah@numfocus.org) or the group organizer.
