The workshop will be a half-day event in the morning of 25th November 2020.
It will be held online.
Please register to get the Zoom link. The registration is now closed, if you would like to attend email us.
You can find technical details about participating and presenting here.
- 8:50 - 9:00: Welcome
- 9:00 - 9:30: Keynote * Judith Gaspers, Amazon: Spoken Language understanding in low-resource scenarios
- 9:30 - 9:45: Break
- 9:45 - 10:30: Presentations
- Thomas Vakili: A method for the assisted translation of QA datasets using multilingual sentence embeddings abstract
- Anouck Braggaar and Rob van der Goot: Creating a universal dependencies treebank of spoken Frisian-Dutch code-switched data
- Rob van der Goot, Marija Stepanovic, Alan Ramponi, Ibrahim Sharaf, Ahmet Üstün, Aizhan Imankulova, Siti Oryza Khairunnisa, Mamoru Komachi and Barbara Plank: Cross-lingual multi-task transfer for zero-shot task-oriented dialog
- 10:30 - 11:00: Coffee break
- 11:00 - 12:00: Presentations
- Ivan Ubaleht: The creation of Siberian Ingrian Finnish and Siberian Tatar speech corpora abstract
- Abir Messaoudi, Hatem Haddad and Chayma Fourati: Sentiment analysis in Tunisian social media using deep learning abstract
- Jemal Abate and Ashenafi Tulu: Development of query-based document summarization for Afaan Oromoo abstract
- Girma Neshir Alemneh, Solomon Atnafu and Andreas Rauber: BERT fine-tuning for Amharic sentiment classification abstract
- 12:00 - 13:00 Lunch break
- 13:00 - 13:30: Keynote * Gabriel Skantze, KTH: Collecting dialogue data for conversational systems
- 13:30 - 14:00: Keynote * Wondwossen Mulugeta, Addis Ababa University: Pure data for NLP
- 14:00 - 14:10: Concluding remarks