Morphological Paradigms: Computational Structure and Unsupervised Learning

Jackson, Lee Ann

doi:10.3115/v1/n15-2022

Cited by 3 publications

(2 citation statements)

References 20 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Boyé and Schalchli (2019) discuss the paradigm cell finding problem, identifying the cell (but not paradigm) realized by a given form. Lee (2015) clusters forms into cells across inflection classes. Beniamine et al (2018) group paradigms into inflection classes, and Eskander et al (2013) induce inflection classes and lemmata from cell labels.…”

Section: Subtasks Of Paradigm Discoverymentioning

confidence: 99%

The Paradigm Discovery Problem

Erdmann¹,

Elsner²,

Wu³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

This work treats the paradigm discovery problem (PDP)-the task of learning an inflectional morphological system from unannotated sentences. We formalize the PDP and develop evaluation metrics for judging systems. Using currently available resources, we construct datasets for the task. We also devise a heuristic benchmark for the PDP and report empirical results on five diverse languages. Our benchmark system first makes use of word embeddings and string similarity to cluster forms by cell and by paradigm. Then, we bootstrap a neural transducer on top of the clustered data to predict words to realize the empty paradigm slots. An error analysis of our system suggests clustering by cell across different inflection classes is the most pressing challenge for future work. Our code and data are available at https://github.com/ alexerdmann/ParadigmDiscovery.

show abstract

Section: Subtasks Of Paradigm Discoverymentioning

confidence: 99%

The Paradigm Discovery Problem

Erdmann¹,

Elsner²,

Wu³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…This means that the Linguistica algorithm for morphological learning must be called and applied flexibly over some growing data. Concretely, we tested Linguistica 5 for its ability to model morphological acquisition using Eve's data in the Brown portion (Brown, 1973) of the CHILDES database (MacWhinney, 2000), an idea sketched in Lee (2015). The child-directed speech (CDS) at different ages of the target child in the data was extracted by the PyLangAcq library (Lee et al, 2016) and fed into Linguistica 5.…”

Section: On Human Morphological Acquisitionmentioning

confidence: 99%

Linguistica 5: Unsupervised Learning of Linguistic Structure

Lee

Goldsmith

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstratio

Self Cite

View full text Add to dashboard Cite

This paper introduces Linguistica 5, a software for unsupervised learning of linguistic structure. It is a descendant of Goldsmith's (2001Goldsmith's ( , 2006 Linguistica. Open-source and written in Python, the new Linguistica 5 is both a graphical user interface software and a Python library. While Linguistica 5 inherits its predecessors' strength in unsupervised learning of natural language morphology, it incorporates significant improvements in multiple ways. Notable new features include tools for data visualization as well as straightforward extensions for both its components and embedding in other programs.

show abstract

Computational Learning of Morphology

Goldsmith

Lee

Xanthos

2017

Annu. Rev. Linguist.

View full text Add to dashboard Cite

This article reviews research on the unsupervised learning of morphology, that is, the induction of morphological knowledge with no prior knowledge of the language beyond the training texts. This is an area of considerable activity over the period from the mid 1990s to the present. It is of particular interest to linguists because it provides a good example of a domain in which complex structures must be induced by the language learner, and successes in this area have all relied on quantitative models that in various ways focus on model complexity and on goodness of fit to the data.

show abstract

Morphological Paradigms: Computational Structure and Unsupervised Learning

Cited by 3 publications

References 20 publications

The Paradigm Discovery Problem

The Paradigm Discovery Problem

Linguistica 5: Unsupervised Learning of Linguistic Structure

Computational Learning of Morphology

Contact Info

Product

Resources

About