UniDive 2nd general meeting
Event title: UniDive 2nd general meeting
Organisation: University of Naples L’Orientale, Department of Literary, Linguistic and Comparative Studies, UNIOR NLP Research Group, Italy
-
Dates: 8-9 February 2024 (co-located with a WG1 meeting on 7 Feb 2024)
-
Program
Wednesday 7 February: WG1 meeting
8:30-9:15 Registration
-
10:30-11:00 coffee break
11:00-12:30 Parallel working sessions I
T1.3 Extensions and updates to morphosyntactic annotation guidelines (
agenda, room 1.1,
zoom link, chairs: Atul Kr. Ojha, Hiwa Asadpour)
T1.2 Pilot PARSEME annotation of non-verbal MWEs (
agenda, room 1.5,
zoom link, chairs: Agata Savary, Voula Giouli, Stella Markanotatou, Sara Stymne, Carlos Ramisch)
12:30-14:00 lunch
14:00-15:30 Parallel working sessions II
T1.4 Manual annotation tools and file formats (
Slides,
agenda, room 1.1, ;
zoom link, chairs: Bruno Guillaume, Frantisek Forgac, A. Seza Doğruöz, Atul Kr. Ojha)
T1.2 Discussion of pilot PARSEME annotation (
agenda, room 1.5,
zoom link, chairs: Agata Savary, Voula Giouli, Stella Markanotatou, Sara Stymne, Carlos Ramisch)
15:30-16:00 coffee break
16:00-17:30 Parallel working sessions III
T1.1 Linguistic typology and multilingual corpus annotation (
agenda, room 1.1,
zoom link, chairs: André Coneglian, Atul Kr. Ojha, A. Seza Doğruöz, Hiwa Asadpour, Manjola Lumani Zaçellari)
T1.2/T1.4 Presentation of the PARSEME pipeline to Language Leaders (
agenda, room 1.5,
zoom link, chairs: Van Tuan Bui, Agata Savary)
For a quick overview of the sessions, see WG1 Day program overview.
Thursday 8 February: 2nd UniDive Workshop
8:15-8:55 registration and poster hanging for session A
8:55-9:00 opening and welcome
9:00-10:30 (session 1,
zoom link; chair: Alina Wróblewska) invited talks:
-
Abstract: In this presentation, I will discuss the training and evaluation of massively multilingual language models, capable of handling dozens or even hundreds of languages. After motivating the development of such models, I will draw some lessons learned in the course of developing Glot500, a language model covering 500 languages, and some associated resources. I will notably focus on the challenges raised by “low-resourced” languages, i.e. languages for which the available learning data is often incomplete, highly specialised and also possibly very noisy.
-
Abstract: We examine the relationship between Africa’s 2000 languages and contemporary language technologies. Our lens focuses on Swahili as a case study, the most widely spoken African language, the one with the most research and technological development, and a representative linguistic model for about 500 other Bantu languages. What has been done, what can be done, and what hasn’t been done for Swahili, and what does this say about 100 other languages with rapidly growing populations that are each spoken by millions of people around Africa?
10:30-11:00 coffee break
-
-
13:00-14:30 lunch, poster hanging for session B
-
-
16:30-16:45 coffee break
16:45-18:00 (session 6; onsite only; room 1.5) Extended Core Group meeting
Social events (details
below):
Friday 9 February: WG sessions
9:00-10:15 (session 7) parallel working sessions
WG1+WG3 (room 1.1; on-site only; chairs: Bruno Guillaume, Kaja Dobrovoljc, Joakim Nivre, Gülşen Eryiğit)
Minutes
WG2+WG4 (room 1.5; chairs: Verginica Mititelu, Voula Giouli, Marie-Catherine de Marneffe, Abigail Walsh)
9:00-9:30 Promote diversity wrt. cross-language unification of lexical features (chairs: Kilian Evang and Dan Zeman)
9:30-10:15 Development of MWE lexica: requirements and challenges (chairs: Stella Markantonatou and Ivelina Stoyanova)
10:15-10:45 coffee break
10:45-12:00 (session 8, on-site only) parallel working sessions
12:00-12:15
group photo 1 2 3
12:15-13:30 lunch
13:30-14:45 (session 9) parallel working sessions
14:45-15:15 coffee break
15:15-16:30 (session 10) parallel working sessions
WG2 (room 1.1; chairs: Verginica Mititelu, Voula Giouli)
15:15-15:40 Task 2.1.2: Harmonizing lemmatization rules (for words and MWEs) (and standardizing lists of lexemes for auxiliaries, pronouns and determiners) (chairs: Dan Zeman and Kilian Evang)
15:40-16:00 Task 2.2: Demonstration of the process of extending the
ELEXIS-WSD corpus with additional annotation layers and other languages (chairs: Jaka Cibej and Carole Tiberius)
-
16:20-16:30 Task 2.3: Survey on existing MWEs lexica: updates (chairs: Stella Markantonatou and Ivelina Stoyanova)
WG4 (room 1.5; chair: Marie-Catherine de Marneffe)
16:30-16:45 break (WG leaders prepare summaries)
16:45-17:30 (session 11; room 1.1) plenary closing session (summary of WG sessions)
Registration
Directions
The event will take place at:
Università degli Studi di Napoli L’Orientale
Palazzo Mediterraneo – Via Nuova Marina, 59, 80133 Napoli
How to get here:
Accommodation
Some recommended hotels are marked in this map.
Please note that Naples is a highly crowded tourist destination even during non-holiday periods. There are many bed and breakfasts in the area adjacent to the university, but we recommend booking accommodation as early as possible.
Meals
Social Events
We plan to have two social events on the 8th of February. The first event is a guided walking tour of the city center. The tour will last approximately one hour and will showcase some of the most iconic places in the city.
Guided walking tour update
We will move from Palazzo del Mediterraneo at 18:00 (not at 18:30) and reach the tour starting point in **Piazza San Domenico - Palazzo Corigliano** to meet our guides. We will move from there at 18:30 for a short (1 hour) guided tour in the city center. Based on the number of participants, we will organize groups of about 30 people.
The second event is a welcome aperitif that will take place at Lazzarelle Bistrot near the National Archaeological Museum. Those who will not participate in the guided tour can reach the venue where the aperitif will be held at 7:30 PM (25 mins on foot, 17 mins by public transportation).
Reimbursement
If you are selected by the Core Group to be reimbursement for the meeting, please accept the invitation that will be sent to you via e-COST before the meeting. After the meeting, fill in the reimbursement form that will be available online via the e-COST system and upload all relevant signed documents, as indicated in the reimbursement form. Before making any arrangements PLEASE READ general rules for the reimbursement described in the COST Annotated Rules, Annex A1-3.1 TRAVEL REIMBURSEMENT RULES. External members (who have not received the e-COST invitation) can also participate freely but will not be reimbursed for their travel and stay. Those external members should also fill in the registration form (to be published soon).
The daily reimbursement rate for this meeting is 160 EUR per night (flat rate). The number of the reimbursed nights is equal to the number of attended workshop/meeting days plus 1 (maximum one night before and one night after the meeting).
Expression of interest
If you are willing to participate in the Naples meeting, please, fill in the expression of interest form.
Please, note that filling in this form does not ensure you an official invite to the meeting or reimbursement of your travel and stay. Decisions about reimbursements will be made starting from late December.