EACL Hackashop on News Media Content Analysis and Automated Report Generation (Hackashop home)
Programme, 19 April 2021
| 9.15 | Plenary session (Zoom) |
| – Opening | |
| – Keynote by Neil Maiden: Co-designing new technologies for journalists to adopt: Experiences from the coalface | |
| – Spotlight presentations of Hackashop contributions | |
| 11.00 | EACL joint coffee break |
| 11.30 | Poster session (gather.town) |
| – Poster presentations of Hackashop contributions (list + schedule) | |
| 13.30 | EACL joint lunch break |
| 15.00 | Plenary session (Zoom) |
| – Roundtable discussion: AI and the future of media | |
| 16.00 | Hackashop end |
Hackashop Proceedings
Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, 19 April 2021. Hannu Toivonen and Michele Boggia, editors. Association for Computational Linguistics. ISBN 978-1-954085-13-8 (link to ACL Anthology)
At 9.30: Keynote
Neil Maiden, Professor of Digital Creativity, City University of London, UK, Co-founder & Chief Product Officer, JECT.AI:
Co-designing new technologies for journalists to adopt: Experiences from the coalface
Abstract: This short keynote will summarise 5 years of experience to co-design a new digital product for journalists to adopt. The product, called JECT.AI, seeks to augment journalist creative thinking to discover and exploit new content, angles and voices for new articles. The JECT.AI team were committed to co-designing the product and trialing early versions of it with journalists. These co-design and trialing experiences gave rise to numerous lessons learned – some predictable, and others not. The keynote will share these experiences, as part of a collaborative process of designing more effective digital technologies for journalists.
Short bio: Neil Maiden is Professor of Digital Creativity at the Business School (formerly Cass) at City, University of London, and Director of the National Centre for Creativity enabled by AI funded by Research England. He is also Chief Product Officer at JECT.AI Limited. His current research interests include uses of artificial intelligence to augment human creativity and enhancing design methods and tools to generate more creative solutions. He is and has been a principal and co-investigator on numerous EPSRC- and EU-funded research projects with a total value of over €73 million. He has published over 220 peer-reviewed papers in academic journals, conferences and workshops proceedings. He was Program Chair for the 12th IEEE International Conference on Requirements Engineering in Kyoto in 2004, and Editor of the IEEE Software’s Requirements column from 2005-2013. His details are available at https://www.city.ac.uk/people/academics/neil-maiden.
At 10.00: Poster spotlights
The spotlight presentations will be given in the order below.
At 11.30: Poster session
| Peer-reviewed workshop papers: | |
| Conforti et al. | Adversarial Training for News Stance Detection: Leveraging Signals from a Multi-Genre Corpus |
| De Los Reyes et al. | Related Named Entities Classification in the Economic-Financial Context |
| Kokalj et al. | BERT meets Shapley: Extending SHAP Explanations to Transformer-based Classifiers |
| Koloski et al. | Extending Neural Keyword Extraction with TF-IDF tagset matching |
| Pelicon et al. | Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection |
| Piskorski et al. | Exploring Linguistically-Lightweight Keyword Extraction Techniques for Indexing News Articles in a Multilingual Set-up |
| Reuver et al. | No NLP Task Should be an Island: Multi-disciplinarity for Diversity in News Recommender Systems |
| Sheehan et al. | TeMoTopic: Temporal Mosaic Visualisation of Topic Distribution, Keywords, and Context |
| Rämö & Leppänen | Using contextual and cross-lingual word embeddings to improve variety in template-based NLG for automated journalism |
| Repar & Shumakov | Aligning Estonian and Russian news industry keywords with the help of subtitle translations and an environmental thesaurus |
| Škrlj et al. | Exploring Neural Language Models via Analysis of Local and Global Self-Attention Spaces |
| Wang | Comment Section Personalization: Algorithmic, Interface, and Interaction Design |
| Žagar & Robnik-Šikonja | Unsupervised Approach to Multilingual User Comments Summarization |
| Resource description: | |
| Pollak et al. | EMBEDDIA Tools, Datasets and Challenges: Resources and Hackathon Contributions |
| Hackathon reports: | |
| Robertson et al. | A COVID-19 news coverage mood map of Europe |
| Koloski et al. | Interesting cross-border news discovery using cross-lingual article linking and document similarity |
| Martinc et al. | Automatic sentiment and viewpoint analysis of Slovenian news corpus on the topic of LGBTIQ+ |
| Korencic et al. | To Block or not to Block: Experiments with Machine Learning for News Comment Moderation |
| Reuver & Mattis | Implementing Evaluation Metrics Based on Theories of Democracy in News Comment Recommendation |
At 15.00: Roundtable on AI and the future of media
Panelists:
| Alexandra Garatzogianni | Head of Knowledge and technology transfer, Leibniz University of Hannover, Germany |
| Senja Pollak | Assistant Professor of Language Technologies and researcher at Jožef Stefan Institute, Slovenia |
| Salla Salmela | Producer Finnish News Agency STT, Finland |
| Agnes Stenbom | Responsible Data and AI Specialist, Schibsted, Sweden |
| Carl-Gustav Linden | Associate Professor, Universities of Bergen, Norway, and Helsinki, Finland; Roundtable Chair |