The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes

List, Johann-Mattis; Vylomova, Ekaterina; Forkel, Robert; Hill, Nathan W.; Cotterell, Ryan D.

Abstract

This study describes the structure and the results of the SIGTYP 2022 shared task on the prediction of cognate reflexes from multilingual wordlists. We asked participants to submit systems that would predict words in individual languages with the help of cognate words from related languages. Training and surprise data were based on standardized multilingual wordlists from several language families. Four teams submitted a total of eight systems, including both neural and non-neural systems, as well as systems adjusted to the task and systems using more general settings. While all systems showed a rather promising performance, reflecting the overwhelming regularity of sound change, the best performance throughout was achieved by a system based on convolutional networks originally designed for image restoration.

Citation

List, J.-M., Vylomova, E., Forkel, R., Hill, N. W., & Cotterell, R. D. (2022). The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes

• Journal Article Type: Article
• Acceptance Date: Jul 8, 2022
• Publication Date: Jul 14, 2022
• Deposit Date: Jul 22, 2022
• Publicly Available Date: Jul 22, 2022
• Journal: Proceedings of the 4th Workshop on Computational Typology and Multilingual NLP (SIGTYP 2022)
• Peer Reviewed: Peer Reviewed
• Pages: 52-62
• Publisher URL: https://sigtyp.github.io/workshops/2022/sigtyp/papers/SIGTYP2022_proceedings.pdf
• Additional Information: Data Access Statement : Data and code for the shared task along with results for all systems are curated GitHub (https:// github.com/sigtyp/ST2022, Version 1.4) and have been archived with Zenodo (https:// doi.org/10.5281/zenodo.6586772).; Additional Information : ISBN: 9781955917933