Skip to content
conftrace_
2022 NAACL NAACL 2022

JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation

Abstract

AbstractThis paper describes the JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morpheme Segmentation. In this paper we describe probabilistic model trained with the Expectation-Maximization algorithm, we provide the results and analyze sources of errors and general limitations of our approach. The model was implemented within our own modular probabilistic framework.

Authors

Jan Bodnár

Topics

Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Optimization & Theory > Stochastic Processes

Keywords

expectation maximization probabilistic model morphological segmentation language processing
Download PDF

More from NAACL 2022

All NAACL 2022 papers →
Beyond Characters: Subword-level Morpheme Segmentation
Word-level Morpheme segmentation using Transformer neural network
Morfessor-enriched features and multilingual training for canonical morphological segmentation
SIGMORPHON–UniMorph 2022 Shared Task 0: Modeling Inflection in Language Acquisition
SIGMORPHON–UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection
SIGMORPHON 2022 Task 0 Submission Description: Modelling Morphological Inflection with Data-Driven and Rule-Based Approaches