Copy
View this email in your browser

EMBEDDIA NEWS

December, 2020
EMBEDDIA Consortium Meeting in December 2020.

We are proud to invite you to our HACKASHOP ON NEWS MEDIA CONTENT ANALYSIS AND AUTOMATED REPORT GENERATION.

In order to encourage scientific and technological advances, the hackashop has a dual format:

(1) a traditional workshop format for discussing scientific advances is combined with
(2) a preceding hackathon-type event in which participants are provided with news media data and a suite of tools to experiment with novel approaches and solutions. 

Participants can choose to participate in only one or in both roles.

The hackashop is organised in conjunction with the 16th conference of the European Chapter of the Association for Computational Linguistics EACL 2021.
  • Hackathon will be held from February 1st until February 21st.
  • Workshop will be held on April 19th or 20th.
CALL FOR HACKATHON PARTICIPATION!

Our virtual hackathon targets doctoral and graduate students, researchers and professionals interested in natural language processing and machine learning. We especially welcome media researchers from social sciences/media studies and private sector representatives to join the cross-disciplinary teams. 

You are free to register as a team or as an individual. We will provide datasets and a suite of tools for optional use in the hackathon and organise structured activities:
  • matchmaking before the event,
  • tutorials to tools, datasets and challenges in the beginning,
  • expert consultancy and coaching through the hackathon,
  • forums for communication and peer support,
  • joint events for sharing work and experiences. 
IMPORTANT HACKATHON DATES
 
  • Jan 18 – Jan 29: Matchmaking period for those seeking for team mates
  • Jan 29: Registration deadline
  • Feb 1 – Feb 21: Hackathon
  • Feb 21: Hackathon reports due
  • Mar 1: Camera-ready versions of reports due
  • Apr 19 or 20: Workshop event
 
CALL FOR WORKSHOP PAPERS!

We welcome work broadly in the area of natural language processing of news media. Cross-disciplinary collaborations of computer scientists with media researchers and other social scientists and collaborations with the media industry are especially welcome. We encourage contributions that address multilingual settings, including but not limited to low-resource languages. 

The workshop day will bring participants together to share new insights from both research- and experimentation-based work.

Accepted, peer-reviewed papers will be published in EACL workshop proceedings. After the meeting, we aim to organize a special issue or an edited book volume with selected, expanded papers from the workshop and brief hackathon contributions.
IMPORTANT WORKSHOP DATES
 
  • Jan 18: Paper submission deadline
  • Feb 18: Notification of acceptance
  • Mar 1: Camera-ready papers due
  • Apr 19 or 20: Workshop date
 
In other news

Members of the EMBEDDIA consortium met with representatives from the Croatian media 24sata in November and presented our tools and solutions for some of the issues faced by the members of their newsroom. More information here.


Some of our recent scientific publications
 
  • Recycling a genre for news automation: The production of Valtteri the Election Bot
"The amount of available digital data is increasing at a tremendous rate. These data, however, are of limited use unless converted into a user-friendly form. We took on this task and built a natural language generation (NLG) driven system that generates journalistic news stories about elections without human intervention."

Authors: Lauri Haapanen, Leo Leppänen
 
 
  • Bisociative Literature-Based Discovery: Lessons Learned and New Word Embedding Approach
"This paper outlines several outlier-based literature mining approaches to bridging term detection and the lessons learned from selected biomedical literature-based discovery applications. The paper addresses also new prospects in bisociative literature-based discovery, proposing an advanced embeddings-based technology for cross-domain literature mining."

Authors: Nada Lavrač, Matej Martinc, Senja Pollak, Maruša Pompe Novak, Bojan Cestnik
 
  • How Furiously Can Colorless Green Ideas Sleep? Sentence Acceptability in Context
"We compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Next, we test unidirectional and bidirectional language models in their ability to predict acceptability ratings. The two sets of experiments provide insights into the cognitive aspects of sentence processing and central issues in the computational modeling of text and discourse."
 
Authors: Jey Han Lau, Carlos Armendariz, Shalom Lappin, Matthew Purver, Chang Shu
 
Twitter
Facebook
Website
Copyright © *|2020|* *|Department of Knowledge Technologies – EMBEDDIA project, Jožef Stefan Institute, Jamova cesta 39, 1000 Ljubljana, Slovenia|*, All rights reserved.

Our mailing address is:
info@embeddia.eu






This email was sent to <<Email Address>>
why did I get this?    unsubscribe from this list    update subscription preferences
EMBEDDIA · Jamova cesta 39 · Department of Knowledge Technologies – EMBEDDIA project, Jožef Stefan Institute · Ljubljana 1000 · Slovenia

Email Marketing Powered by Mailchimp