TY - GEN
T1 - Linguist vs. Machine: Rapid Development of Finite-State Morphological Grammars
AU - Beemer, Sarah
AU - Boston, Zak
AU - Bukoski, April
AU - Chen, Daniel
AU - Dickens, Princess
AU - Gerlach, Andrew
AU - Hopkins, Torin
AU - Jawale, Parth Anand
AU - Koski, Chris
AU - Malhotra, Akanksha
AU - Mishra, Piyush
AU - Muradoglu, Saliha
AU - Sang, Lan
AU - Short, Tyler
AU - Shreevastava, Sagarika
AU - Spaulding, Elizabeth
AU - Umada, Tetsumichi
AU - Xiang, Beilei
AU - Yang, Changbing
AU - Hulden, Mans
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - Sequence-to-sequence models have proven to be highly successful in learning morphological inflection from examples as the series of SIGMORPHON/CoNLL shared tasks have shown. It is usually assumed, however, that a linguist working with inflectional examples could in principle develop a gold standard-level morphological analyzer and generator that would surpass a trained neural network model in accuracy of predictions, but that it may require significant amounts of human labor. In this paper, we discuss an experiment where a group of people with some linguistic training develop 25+ grammars as part of the shared task and weigh the cost/benefit ratio of developing grammars by hand. We also present tools that can help linguists triage difficult complex morphophonological phenomena within a language and hypothesize inflectional class membership. We conclude that a significant development effort by trained linguists to analyze and model morphophonological patterns are required in order to surpass the accuracy of neural models.
AB - Sequence-to-sequence models have proven to be highly successful in learning morphological inflection from examples as the series of SIGMORPHON/CoNLL shared tasks have shown. It is usually assumed, however, that a linguist working with inflectional examples could in principle develop a gold standard-level morphological analyzer and generator that would surpass a trained neural network model in accuracy of predictions, but that it may require significant amounts of human labor. In this paper, we discuss an experiment where a group of people with some linguistic training develop 25+ grammars as part of the shared task and weigh the cost/benefit ratio of developing grammars by hand. We also present tools that can help linguists triage difficult complex morphophonological phenomena within a language and hypothesize inflectional class membership. We conclude that a significant development effort by trained linguists to analyze and model morphophonological patterns are required in order to surpass the accuracy of neural models.
UR - http://www.scopus.com/inward/record.url?scp=85095293458&partnerID=8YFLogxK
U2 - 10.18653/v1/2020.sigmorphon-1.18
DO - 10.18653/v1/2020.sigmorphon-1.18
M3 - Conference contribution
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 162
EP - 170
BT - Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
PB - Association for Computational Linguistics (ACL)
T2 - 17th SIGMORPHON Workshop on Computational Research in Phonetics Phonology, and Morphology, SIGMORPHON 2020 as part of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Y2 - 10 July 2020
ER -