1 |
Morphological Processing of Low-Resource Languages: Where We Are and What's Next ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation? ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Jump-Starting Item Parameters for Adaptive Language Tests ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions
|
|
|
|
In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Predicting Declension Class from Form and Meaning
|
|
|
|
In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
|
|
Abstract:
The noun lexica of many natural languages are divided into several declension classes with characteristic morphological properties. Class membership is far from deterministic, but the phonological form of a noun and/or its meaning can often provide imperfect clues. Here, we investigate the strength of those clues. More specifically, we operationalize this by measuring how much information, in bits, we can glean about declension class from knowing the form and/or meaning of nouns. We know that form and meaning are often also indicative of grammatical gender—which, as we quantitatively verify, can itself share information with declension class—so we also control for gender. We find for two Indo-European languages (Czech and German) that form and meaning respectively share significant amounts of information with class (and contribute additional information above and beyond gender). The three-way interaction between class, form, and meaning (given gender) is also significant. Our study is important for two reasons: First, we introduce a new method that provides additional quantitative support for a classic linguistic finding that form and meaning are relevant for the classification of nouns into declensions. Secondly, we show not only that individual declensions classes vary in the strength of their clues within a language, but also that these variations themselves vary across languages.
|
|
URL: https://doi.org/10.3929/ethz-b-000462306 https://hdl.handle.net/20.500.11850/462306
|
|
BASE
|
|
Hide details
|
|
8 |
UniMorph 3.0: Universal Morphology
|
|
|
|
In: Proceedings of the 12th Language Resources and Evaluation Conference (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Modeling Color Terminology Across Thousands of Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Marrying Universal Dependencies and Universal Morphology ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|