Morphology Without Borders: Clause-Level Morphology

Omer Goldman, Reut Tsarfaty

Research output: Contribution to journalArticlepeer-review

Abstract

Morphological tasks use large multi-lingual datasets that organize words into inflection tables, which then serve as training and evaluation data for various tasks. However, a closer inspection of these data reveals pro-found cross-linguistic inconsistencies, which arise from the lack of a clear linguistic and operational definition of what is a word, and which severely impair the universality of the derived tasks. To overcome this deficiency, we propose to view morphology as a clause-level phenomenon, rather than word-level. It is an-chored in a fixed yet inclusive set of features, that encapsulates all functions realized in a saturated clause. We deliver MIGHTYMORPH, a novel dataset for clause-level morphology covering 4 typologically different languages: English, German, Turkish, and Hebrew. We use this dataset to derive 3 clause-level morphological tasks: inflection, reinflection and analysis. Our experiments show that the clause-level tasks are substantially harder than the respective word-level tasks, while having comparable complexity across languages. Furthermore, redefining morphology to the clause-level provides a neat interface with contextualized language models (LMs) and allows assessing the morphological knowledge encoded in these models and their usabil-ity for morphological tasks. Taken together, this work opens up new horizons in the study of computational morphology, leaving ample space for studying neural morphology cross-linguistically.

Original languageEnglish
Pages (from-to)1455-1472
Number of pages18
JournalTransactions of the Association for Computational Linguistics
Volume10
DOIs
StatePublished - 2022
Externally publishedYes

Bibliographical note

Funding Information:
We would like to thank the TACL anonymous reviewers and the action editor for their insightful suggestions and remarks. This work was supported funded by an ERC-StG grant from the European Research Council, grant number 677352 (NLPRO), and by an innovation grant by the Ministry of Science and Technology (MOST) 0002214, for which we are grateful.

Publisher Copyright:
© 2022 Association for Computational Linguistics. All rights reserved.

Fingerprint

Dive into the research topics of 'Morphology Without Borders: Clause-Level Morphology'. Together they form a unique fingerprint.

Cite this