Morphological Processing of Low-Resource Languages: Where We Are and What's Next
Automatic morphological processing can aid downstream natural language processing
applications, especially for low-resource languages, and assist language documentation …
applications, especially for low-resource languages, and assist language documentation …
Miller's monkey updated: Communicative efficiency and the statistics of words in natural language
Is language designed for communicative and functional efficiency? GK Zipf famously argued
that shorter words are more frequent because they are easier to use, thereby resulting in the …
that shorter words are more frequent because they are easier to use, thereby resulting in the …
[PDF][PDF] Computational models of morphological learning
J Kodner - Oxford Research Encyclopedia of Linguistics, 2022 - lingbuzz.net
The most elucidating computational model of morphology learning from the perspective of a
linguist is one that learns morphology like a child does, that is, on child-like input and along …
linguist is one that learns morphology like a child does, that is, on child-like input and along …
Unsupervised morphological segmentation in a language with reduplication
We present an extension of the Morfessor Baseline model of unsupervised morphological
segmentation (Creutz and Lagus, 2007) that incorporates abstract templates for …
segmentation (Creutz and Lagus, 2007) that incorporates abstract templates for …
Learning morphological productivity as meaning-form mappings
Child language acquisition is famously accurate despite the sparsity of linguistic input. In this
paper, we introduce a cognitively motivated method for morphological acquisition with a …
paper, we introduce a cognitively motivated method for morphological acquisition with a …
Quantifying synthesis and fusion and their impact on machine translation
Theoretical work in morphological typology offers the possibility of measuring morphological
diversity on a continuous scale. However, literature in Natural Language Processing (NLP) …
diversity on a continuous scale. However, literature in Natural Language Processing (NLP) …
A Principled Framework for Evaluating on Typologically Diverse Languages
Beyond individual languages, multilingual natural language processing (NLP) research
increasingly aims to develop models that perform well across languages generally …
increasingly aims to develop models that perform well across languages generally …
More than Just Statistical Recurrence: Human and Machine Unsupervised Learning of M\= aori Word Segmentation across Morphological Processes
A Varatharaj, S Todd - arXiv preprint arXiv:2403.14444, 2024 - arxiv.org
Non-M\= aori-speaking New Zealanders (NMS) are able to segment M\= aori words in a
highlysimilar way to fluent speakers (Panther et al., 2024). This ability is assumed to derive …
highlysimilar way to fluent speakers (Panther et al., 2024). This ability is assumed to derive …
[PDF][PDF] Meaning-Informed Low-Resource Segmentation of Agglutinative Morphology
C Belth - Proceedings of the Society for Computation in …, 2024 - aclanthology.org
Morphological segmentation is both an interesting acquisition problem and an important
task for natural language processing. Most current computational approaches either use …
task for natural language processing. Most current computational approaches either use …
Inducing Meaningful Units from Character Sequences with Slot Attention
M Behjati, J Henderson - arXiv preprint arXiv:2102.01223, 2021 - arxiv.org
Characters do not convey meaning, but sequences of characters do. We propose an
unsupervised distributional method to learn the abstract meaning-bearing units in a …
unsupervised distributional method to learn the abstract meaning-bearing units in a …