====== Morphological Analysis ====== ===== Overviews ===== * Morphological analysis with FSTs: [[https://github.com/rain1024/slp2-pdf/blob/master/chapter-wise-pdf/%5B03%5D%20Words%20%26%20Transducers.pdf|Speech and Language Processing 2nd Ed, Ch 3]] * Lecture: [[https://classes.soe.ucsc.edu/nlp201/Fall20/slides/morphology-fst.pdf|NLP 201 - Fall 2020 Oct 15]] * Related work of [[https://aclanthology.org/N13-1140.pdf|Chahuneau 2013]] (section 6) gives a very quick overview ===== Unsupervised Analysers ===== * [[https://proceedings.neurips.cc/paper/2005/file/4b21cf96d4cf612f239a6c322b10c8fe-Paper.pdf|Goldwater et al 2005 - Interpolating Between Types and Tokens by Estimating Power-Law Generators]] "We show that taking a particular stochastic process – the Pitman-Yor process – as an adaptor justifies the appearance of type frequencies in formal analyses of natural language, and improves the performance of a model for unsupervised learning of morphology." * [[https://aclanthology.org/N13-1140.pdf|Chahuneau et al 2013 - Knowledge-Rich Morphological Priors for Bayesian Language Models]] Combines a finite-state guesser (that was constructed in 3 hours) with Bayesian non-parametrics to learn the correct morphological analysis. Limitation: assumes each word has one best morphological analysis, taken out of context. This could be corrected with contextualized model, like a sequence model for the part-of-speech tags ===== Neural Analysers ===== * [[https://arxiv.org/pdf/2005.05477.pdf|Schwartz et al 2019 - Neural Polysynthetic Language Modelling]] ===== Finite-State Analysers ===== * Software * [[https://fomafst.github.io/|Foma]] * Tutorials * [[https://fomafst.github.io/morphtut.html|Tutorial - Building a Finite-State Morphological Analyzer]] * Papers * [[https://www.aclweb.org/anthology/2020.lrec-1.326.pdf|Chen et al 2020 - Improved Finite-State Morphological Analysis for St. Lawrence Island Yupik Using Paradigm Function Morphology]] ===== People ===== * [[https://scholar.google.com/citations?user=J8a1zEwAAAAJ&hl=en|Lane Schwartz]] ===== Related Pages ===== * [[FSAs and FSTs]] * [[linguistics:Morphology]]