BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:HIPE-2022: Shared Task on Named Entity Recognition and Linking in 
 Multilingual Historical Documents
DTSTART;VALUE=DATE:20220215
DTSTAMP:20260406T224434Z
UID:0127f4f5af3aacbb00055e5ce9c349751c9cb925b9703459ecce9858
CATEGORIES:Miscellaneous
DESCRIPTION:\n\n\n\n\n\nThe HIPE evaluation lab series is organized by res
 earchers from the EPFL Digital Humanities Lab (DHLAB)\, the University of 
 Lausanne\, the University of Zurich\, and the University of La Rochelle. T
 he organizers are inviting participation in the second edition of the HIPE
  shared task on named entity processing in historical documents as part of
  CLEF 2022 Evaluation Labs. \n\n\n\n \n\n\n\nThe HIPE evaluation lab ser
 ies is part of the ongoing efforts of the natural language processing and 
 digital humanities communities to adapt and develop appropriate technologi
 es to efficiently retrieve and explore information from historical texts. 
 On such material\, however\, named entity processing techniques face the c
 hallenges of domain and document type heterogeneity\, input noisiness\, dy
 namics of language\, and lack of resources. \n\n\n\n \n\n\n\nFollowing t
 he first CLEF-HIPE-2020 evaluation lab on historical newspapers in three
  languages\, HIPE-2022 confronts systems with the challenges of dealing wi
 th more languages\, learning domain-specific entities\, and adapting to di
 verse annotation tag sets. The objective is to gain new insights into the 
 transferability of named entity processing approaches across languages\, t
 ime periods\, document types\, and annotation tag sets.\n\n\n\n\n\n \n\n\
 n\nTasks\n\n\n\n- Named Entity Recognition and Classification (coarse and 
 fine-grained tasks).\n\n\n\n- Entity Linking (with and without prior infor
 mation on entity mentions).\n\n\n\n \n\n\n\nData\n\n\n\n\n\nHIPE-2022 dat
 asets are based on six primary datasets assembled and prepared for the sha
 red task. Primary datasets are composed of historical newspapers and class
 ic commentaries covering ca. 200 years. They feature several languages as 
 well as different entity tag sets and annotation schemes. They originate f
 rom several European cultural heritage projects\, from HIPE organizers’ 
 previous research project\, and from the previous HIPE-2020 campaign. Some
  are already published\, others are released for the first time for HIPE-2
 022.\n\n\n\n\n\n\nTracks and Challenges\n\n\n\n\nTo accommodate the differ
 ent dimensions that characterize HIPE-2022 (tasks\, languages\, document t
 ypes\, entity tag sets) and foster research on transferability\, the evalu
 ation lab is organized around challenges and tracks.\n\n\n\n\n \n\n\n\
 nA track is a specific triple composed of the test sets of [dataset-langua
 ge-task] and a challenge is a predefined set of tracks (a challenge can be
  seen as a kind of championship with multiple tracks).\n\n\n\n \n\n\n\n\n
 \nHIPE-2022 specifically evaluates 3 challenges:\n\n\n\n \n\n\n\n1. Mult
 ilingual Newspaper Challenge: newspaper datasets only\, 2 languages min\;\
 n\n\n\n\n2. Multilingual Classical Commentary Challenge: commentary datas
 ets only\, 3 languages min\;\n\n\n\n3. Global Adaptation Challenge: submi
 tted tracks must include both document types\, 2 languages min.  \n\nPrac
 tical information\n\nHIPE-2022 website: https://hipe-eval.github.io/HIPE-
 2022/  \nRegistration: https://clef2022-labs-registration.dei.unipd.it/
  (until 22 April 2022)\n\n\n\n\nParticipation Guidelines: https://doi.org
 /10.5281/zenodo.6045662\n\n\n\nHIPE-2022-data GitHub repository: https://
 github.com/hipe-eval/HIPE-2022-data \n\n\n\nWorkshop venue: during CLEF c
 onference\, 5-8 September 2022\, Bologna\, Italy.\nTwitter: #HIPE2022 / @c
 lef_initiative / #clef2022\n\n\n\n\n\n\n\n\n\n \n\n\n\n\n\n
LOCATION:https://hipe-eval.github.io/HIPE-2022/
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR