Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion

Many of the world’s languages contain an abundance of inflected forms for each lexeme. A critical task in processing such languages is predicting these inflected forms. We develop a novel statistical model for the problem, drawing on graphical modeling techniques and recent advances in deep learning. We derive a Metropolis-Hastings algorithm to jointly decode the model. Our Bayesian network draws inspiration from principal parts morphological analysis. We demonstrate improvements on 5 languages.

Computer Science Linguistics

View graph Source

Paper

Full text

Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion

Semantic Scholar · Computer Science · 2017

Abstract

Many of the world’s languages contain an abundance of inflected forms for each lexeme. A critical task in processing such languages is predicting these inflected forms. We develop a novel statistical model for the problem, drawing on graphical modeling techniques and recent advances in deep learning. We derive a Metropolis-Hastings algorithm to jointly decode the model. Our Bayesian network draws inspiration from principal parts morphological analysis. We demonstrate improvements on 5 languages.

Source of record · Semantic Scholar

Similar papers

Neural Factor Graph Models for Cross-lingual Morphological TaggingChaitanya Malaviya, Matthew R. Gormley, Graham Neubig2018 · Annual Meeting of the Association for Computational Linguistics · 31 citations In Library

Modeling Word Forms Using Latent Underlying Morphs and PhonologyRyan Cotterell, Nanyun Peng, Jason Eisner2015 · Transactions of the Association for Computational Linguistics · 47 citations In Library

Contextualization of Morphological InflectionEkaterina Vylomova, Ryan Cotterell, Timothy Baldwin et al.2019 · North American Chapter of the Association for Computational Linguistics · 5 citations In Library

Unsupervised Inflection Generation Using Neural Language ModelingOctavia Maria Sulea, S. Young2019 · International Work-Conference on Artificial and Natural Neural Networks · 0 citations In Library

Building neural network models for morphological and morpheme analysis of textsAlexander S. Sapin2021 · Proceedings of the Institute for System Programming of RAS In Library

Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language ModelingJakob Prange, Nathan Schneider, Lingpeng Kong2021 · arXiv (Cornell University) · 16 citations In Library

Neural Polysynthetic Language ModellingLane Schwartz, Francis M. Tyers, Lori Levin et al.2020 · arXiv (Cornell University) In Library

Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language ModelingJakob Prange, Nathan Schneider, Lingpeng Kong2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies In Library

Deep Neural Networks for Syntactic Parsing of Morphologically Rich LanguagesJoël Legrand, R. Collobert2016 · Annual Meeting of the Association for Computational Linguistics · 8 citations In Library

Linguistically inspired morphological inflection with a sequence to sequence modelEleni Metheniti, Guenter Neumann, Josef van Genabith2020 · arXiv (Cornell University) · 1 citation In Library

Source of record

Semantic Scholar

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal