Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors

no code implementations • Findings (ACL) 2021 • Ramy Eskander, Cass Lowry, Sujay Khandagale, Francesca Callejas, Judith Klavans, Maria Polinsky, Smaranda Muresan

Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages

1 code implementation • NAACL 2022 • Ramy Eskander, Cass Lowry, Sujay Khandagale, Judith Klavans, Maria Polinsky, Smaranda Muresan

Our results show that the stem-based approach improves the POS models for all the target languages, with an average relative error reduction of 10. 3% in accuracy per target language, and outperforms the word-based approach that operates on three-times more data for about two thirds of the language pairs we consider.

Part-Of-Speech Tagging POS +1

MorphAGram, Evaluation and Framework for Unsupervised Morphological Segmentation

no code implementations • LREC 2020 • Esk, Ramy er, Francesca Callejas, Elizabeth Nichols, Judith Klavans, Smar Muresan, a

Computational morphological segmentation has been an active research topic for decades as it is beneficial for many natural language processing tasks.

Segmentation

Unsupervised Morphological Segmentation for Low-Resource Polysynthetic Languages

no code implementations • WS 2019 • Esk, Ramy er, Judith Klavans, Smar Muresan, a

Polysynthetic languages pose a challenge for morphological analysis due to the root-morpheme complexity and to the word class {``}squish{''}.

Morphological Analysis

Challenges in Speech Recognition and Translation of High-Value Low-Density Polysynthetic Languages

no code implementations • WS 2018 • Judith Klavans, John Morgan, Stephen LaRocca, Jeffrey Micher, Clare Voss

Automatic Speech Recognition (ASR) Machine Translation +2