RECORD
Morphology Without Borders: Clause-Level Morphology
Computation and Language · Submitted 25 Feb 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Taken together, this work opens up new horizons in the study of computational morphology, leaving ample space for studying neural morphology cross-linguistically.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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 profound cross-linguistic inconsistencies, that arise from the lack of a clear linguistic and operational definition of what is a word, and that 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 anchored 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 usability 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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Morphological tasks use large multi-lingual datasets that organize words into inflection tables, which then serve as training and evaluation data for various tasks. | background 1.00 | 0.07 | 0.02 | asserted 1.00 |
| s1 | However, a closer inspection of these data reveals profound cross-linguistic inconsistencies, that arise from the lack of a clear linguistic and operational definition of what is a word, and that severely impair the universality of the derived tasks. | gap 0.83 | 0.50 | 0.06 | asserted 1.00 |
| s2 | To overcome this deficiency, we propose to view morphology as a clause-level phenomenon, rather than word-level. | contribution 0.91 | 0.50 | 0.15 | asserted 0.83 |
| s3 | It is anchored in a fixed yet inclusive set of features, that encapsulates all functions realized in a saturated clause. | method 0.60 | 0.42 | 0.08 | asserted 1.00 |
| s4 | We deliver MightyMorph, a novel dataset for clause-level morphology covering 4 typologically-different languages: English, German, Turkish and Hebrew. | contribution 0.80 | 0.96 | 0.06 | asserted 1.00 |
| s5 | We use this dataset to derive 3 clause-level morphological tasks: inflection, reinflection and analysis. | method 0.65 | 0.96 | 0.05 | asserted 0.99 |
| s6 | Our experiments show that the clause-level tasks are substantially harder than the respective word-level tasks, while having comparable complexity across languages. | result 1.00 | 0.96 | 0.28 | asserted 1.00 |
| s7 | 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 usability for morphological tasks. | interpretation 0.82 | 0.52 | 0.18 | asserted 0.96 |
| s8 | Taken together, this work opens up new horizons in the study of computational morphology, leaving ample space for studying neural morphology cross-linguistically. | future work 0.69 | 0.33 | 0.31 | asserted 0.79 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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 profound cross-linguistic inconsistencies, that arise from the lack of a clear linguistic and operational definition of what is a word, and that 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 anchored 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 usability 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.
Human review
How the literature uses it
1 arXiv paper cite this in 1 sentence
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.