Universality, diversity and idiosyncrasy
in language technology
CA21167 COST Action

User Tools

Site Tools

Trace: • reports • wg4-meeting
meetings:general_meetings:2nd_unidive_general_meeting

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
meetings:general_meetings:2nd_unidive_general_meeting [2024/02/10 10:20] – [Program] ranka.stankovicmeetings:general_meetings:2nd_unidive_general_meeting [2025/07/04 15:27] (current) – [Program Chairs] agata.savary
Line 8: Line 8:
  
 |[[https://www.cost.eu/|{{ :cost_logo_rgb_lowresolution-cropped.jpg?80 |}}]]|{{ :en-funded_by_the_eu-pos.png?150 |}}|[[https://www.unior.it/en/|{{ :meetings:general_meetings:naples-logo.png?100 |}}]]| |[[https://www.cost.eu/|{{ :cost_logo_rgb_lowresolution-cropped.jpg?80 |}}]]|{{ :en-funded_by_the_eu-pos.png?150 |}}|[[https://www.unior.it/en/|{{ :meetings:general_meetings:naples-logo.png?100 |}}]]|
 +
 +{{ :meetings:general_meetings:2nd_unidive_general_meeting:group-naples.jpg?1000 |}}
 +
 +===== Program committee =====
 +See [[meetings:general_meetings:2nd_unidive_general_meeting_call_for_abstracts#program_chairs|here]].
  
 ===== Program =====  ===== Program ===== 
  
-All sessions take place at the University of Naples “L’Orientale”, [[http://www.sod.unior.it/da/mediterraneo/piano_uno.html|Palazzo Mediterraneo]], rooms 1.1 and 1.5. To know more about the posters, see the [[meetings:general_meetings:2nd_unidive_general_meeting:abstracts|call for abstracts]].+All sessions take place at the University of Naples “L’Orientale”, [[http://www.sod.unior.it/da/mediterraneo/piano_uno.html|Palazzo Mediterraneo]], rooms 1.1 and 1.5. To know more about the posters, see the [[meetings:general_meetings:2nd_unidive_general_meeting_call_for_abstracts|call for abstracts]].
  
-=== Wednesday 7 February: WG1 meeting === +==== Wednesday 7 February: WG1 meeting ==== 
   * 8:30-9:15 Registration   * 8:30-9:15 Registration
   * 9:15-10:30 [[https://docs.google.com/presentation/d/1E9wmU3aAo8ivUrH7Pnsn_t3HxMx9dlJViQmJ4PnJ2S4/edit#slide=id.p|Opening session]] (room 1.1; [[https://us02web.zoom.us/j/82123620164?pwd=NEdTajNFRmVDZTYrS0ZYYy9SRTFpUT09|zoom link]]; chairs: Bruno Guillaume, Kaja Dobrovoljc)   * 9:15-10:30 [[https://docs.google.com/presentation/d/1E9wmU3aAo8ivUrH7Pnsn_t3HxMx9dlJViQmJ4PnJ2S4/edit#slide=id.p|Opening session]] (room 1.1; [[https://us02web.zoom.us/j/82123620164?pwd=NEdTajNFRmVDZTYrS0ZYYy9SRTFpUT09|zoom link]]; chairs: Bruno Guillaume, Kaja Dobrovoljc)
Line 35: Line 40:
 For a quick overview of the sessions, see [[https://docs.google.com/document/d/1mNXff6gOP0FBfCBwhaR0SZqAT8wgX961qL95NWuW0KY/edit?usp=sharing|WG1 Day program overview]]. For a quick overview of the sessions, see [[https://docs.google.com/document/d/1mNXff6gOP0FBfCBwhaR0SZqAT8wgX961qL95NWuW0KY/edit?usp=sharing|WG1 Day program overview]].
  
-=== Thursday 8 February: 2nd UniDive Workshop ===+==== Thursday 8 February: 2nd UniDive Workshop ====
   * 8:15-8:55 registration and poster hanging for session A   * 8:15-8:55 registration and poster hanging for session A
   * 8:55-9:00 opening and welcome   * 8:55-9:00 opening and welcome
   * 9:00-10:30 (session 1, [[https://us02web.zoom.us/j/82123620164?pwd=NEdTajNFRmVDZTYrS0ZYYy9SRTFpUT09|zoom link]]; chair: Alina Wróblewska) invited talks:   * 9:00-10:30 (session 1, [[https://us02web.zoom.us/j/82123620164?pwd=NEdTajNFRmVDZTYrS0ZYYy9SRTFpUT09|zoom link]]; chair: Alina Wróblewska) invited talks:
-    * 9:00-9:45 [[https://www.isir.upmc.fr/personnel/yvon?lang=en|François Yvon]] (Sorbonne Université, CNRS, Inserm) - //Training and evaluating massively multilingual language models//+    * 9:00-9:45 [[https://www.isir.upmc.fr/personnel/yvon?lang=en|François Yvon]] (Sorbonne Université, CNRS, Inserm) - //{{ :meetings:general_meetings:2nd_unidive_general_meeting:unidive-naples-francois-yvon-multilingual.pdf|Training and evaluating massively multilingual language models}}//
       * __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__: 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.
-    * 9:45-10:30 [[https://afrykanistyka.uw.edu.pl/en/beata-wojtowicz/|Beata Wójtowicz]] (University of Warsaw) and [[https://www.youtube.com/@pirateprofessor/about|Martin Benjamin]] (Kamusi Project International) - //African Languages in the Technological Realm//+    * 9:45-10:30 [[https://afrykanistyka.uw.edu.pl/en/beata-wojtowicz/|Beata Wójtowicz]] (University of Warsaw) and [[https://www.youtube.com/@pirateprofessor/about|Martin Benjamin]] (Kamusi Project International) - //{{ :meetings:general_meetings:2nd_unidive_general_meeting:unidive_naples_2024_invited_talk.pdf |African Languages in the Technological Realm}}//
       * __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?       * __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//   * 10:30-11:00 //coffee break//
Line 56: Line 61:
     * 19:30 A welcome cocktail     * 19:30 A welcome cocktail
  
-=== Friday 9 February: WG sessions ===+==== Friday 9 February: WG sessions ====
   * 9:00-10:15 (session 7) parallel working 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) [[https://docs.google.com/document/d/14ldehPHr6I7Y9Ow6DyNQuYnQzCv_KWMpnAlDC-CPMyo/edit?usp=sharing|Minutes]]     * WG1+WG3 (room 1.1; on-site only; chairs: Bruno Guillaume, Kaja Dobrovoljc, Joakim Nivre, Gülşen Eryiğit) [[https://docs.google.com/document/d/14ldehPHr6I7Y9Ow6DyNQuYnQzCv_KWMpnAlDC-CPMyo/edit?usp=sharing|Minutes]]
Line 73: Line 78:
       * 10:45-11:15 Presentations from both WGs on NLP resource documentation tasks undertaken in WG3 and WG4 (T3.1, T4.1) (chair: Lucia Amoros Poveda)       * 10:45-11:15 Presentations from both WGs on NLP resource documentation tasks undertaken in WG3 and WG4 (T3.1, T4.1) (chair: Lucia Amoros Poveda)
       * 11:15-12:00 Short presentation of (a) shared task (T3.2) by WG3 and (b) metrics by WG4, followed by discussions (chair: Joakim Nivre)       * 11:15-12:00 Short presentation of (a) shared task (T3.2) by WG3 and (b) metrics by WG4, followed by discussions (chair: Joakim Nivre)
-        * [[https://docs.google.com/presentation/d/1Bc2opirzgoPV_tFp-qshS5YZ9I_-QqCcb8VlrZh2Oh0/edit#slide=id.g27baaceb0db_0_281|Shared task presentation]]* +        * [[https://docs.google.com/presentation/d/1Bc2opirzgoPV_tFp-qshS5YZ9I_-QqCcb8VlrZh2Oh0/edit#slide=id.g27baaceb0db_0_281|Shared task presentation]] (Omer Goldman) 
-        * {{ :meetings:general_meetings:2nd_unidive_general_meeting:louis-main2.pdf|slides on metrics (by Louis)}}+        * {{ :meetings:general_meetings:2nd_unidive_general_meeting:louis-main2.pdf|Diversity metrics for the shared task}} (Louis Estève)
   * 12:00-12:15 //group photo// {{:meetings:general_meetings:2024-02-09_14-23-23.jpg?linkonly|1}} {{ :meetings:general_meetings:2024-02-09_14-23-26.jpg?linkonly |2}} {{ :meetings:general_meetings:2024-02-09_14-23-49.jpg?linkonly |3}}   * 12:00-12:15 //group photo// {{:meetings:general_meetings:2024-02-09_14-23-23.jpg?linkonly|1}} {{ :meetings:general_meetings:2024-02-09_14-23-26.jpg?linkonly |2}} {{ :meetings:general_meetings:2024-02-09_14-23-49.jpg?linkonly |3}}
   * 12:15-13:30 //lunch//   * 12:15-13:30 //lunch//
meetings/general_meetings/2nd_unidive_general_meeting.1707556832.txt.gz · Last modified: by ranka.stankovic