TY - GEN
T1 - SIGMORPHON-UniMorph 2022 Shared Task 0
T2 - 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, SIGMORPHON 2022
AU - Kodner, Jordan
AU - Khalifa, Salam
AU - Batsuren, Khuyagbaatar
AU - Dolatian, Hossep
AU - Cotterell, Ryan
AU - Akkuş, Faruk
AU - Anastasopoulos, Antonios
AU - Andrushko, Taras
AU - Arora, Aryaman
AU - Bella, Nona Atanelov Gábor
AU - Budianskaya, Elena
AU - Ghanggo Ate, Yustinus
AU - Goldman, Omer
AU - Guriel, David
AU - Guriel, Simon
AU - Guriel-Agiashvili, Silvia
AU - Kieraś, Witold
AU - Krizhanovsky, Andrew
AU - Krizhanovsky, Natalia
AU - Marchenko, Igor
AU - Markowska, Magdalena
AU - Mashkovtseva, Polina
AU - Nepomniashchaya, Maria
AU - Rodionova, Daria
AU - Sheifer, Karina
AU - Serova, Alexandra
AU - Yemelina, Anastasia
AU - Young, Jeremiah
AU - Vylomova, Ekaterina
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - The 2022 SIGMORPHON-UniMorph shared task on large scale morphological inflection generation included a wide range of typologically diverse languages: 33 languages from 11 top-level language families: Arabic (Modern Standard), Assamese, Braj, Chukchi, Eastern Armenian, Evenki, Georgian, Gothic, Gujarati, Hebrew, Hungarian, Itelmen, Karelian, Kazakh, Ket, Khalkha Mongolian, Kholosi, Korean, Lamahalot, Low German, Ludic, Magahi, Middle Low German, Old English, Old High German, Old Norse, Polish, Pomak, Slovak, Turkish, Upper Sorbian, Veps, and Xibe. We emphasize generalization along different dimensions this year by evaluating test items with unseen lemmas and unseen features separately under small and large training conditions. Across the six submitted systems and two baselines, the prediction of inflections with unseen features proved challenging, with average performance decreased substantially from last year. This was true even for languages for which the forms were in principle predictable, which suggests that further work is needed in designing systems that capture the various types of generalization required for the world's languages.
AB - The 2022 SIGMORPHON-UniMorph shared task on large scale morphological inflection generation included a wide range of typologically diverse languages: 33 languages from 11 top-level language families: Arabic (Modern Standard), Assamese, Braj, Chukchi, Eastern Armenian, Evenki, Georgian, Gothic, Gujarati, Hebrew, Hungarian, Itelmen, Karelian, Kazakh, Ket, Khalkha Mongolian, Kholosi, Korean, Lamahalot, Low German, Ludic, Magahi, Middle Low German, Old English, Old High German, Old Norse, Polish, Pomak, Slovak, Turkish, Upper Sorbian, Veps, and Xibe. We emphasize generalization along different dimensions this year by evaluating test items with unseen lemmas and unseen features separately under small and large training conditions. Across the six submitted systems and two baselines, the prediction of inflections with unseen features proved challenging, with average performance decreased substantially from last year. This was true even for languages for which the forms were in principle predictable, which suggests that further work is needed in designing systems that capture the various types of generalization required for the world's languages.
UR - https://www.scopus.com/pages/publications/85139098980
M3 - Conference contribution
AN - SCOPUS:85139098980
T3 - SIGMORPHON 2022 - 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, Proceedings of the Workshop
SP - 176
EP - 203
BT - SIGMORPHON 2022 - 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, Proceedings of the Workshop
A2 - Nicolai, Garrett
A2 - Chodroff, Eleanor
PB - Association for Computational Linguistics (ACL)
Y2 - 14 July 2022
ER -