Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning

Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo


Abstract
Data-driven segmentation of words into subword units has been used in various natural language processing applications such as automatic speech recognition and statistical machine translation for almost 20 years. Recently it has became more widely adopted, as models based on deep neural networks often benefit from subword units even for morphologically simpler languages. In this paper, we discuss and compare training algorithms for a unigram subword model, based on the Expectation Maximization algorithm and lexicon pruning. Using English, Finnish, North Sami, and Turkish data sets, we show that this approach is able to find better solutions to the optimization problem defined by the Morfessor Baseline model than its original recursive training algorithm. The improved optimization also leads to higher morphological segmentation accuracy when compared to a linguistic gold standard. We publish implementations of the new algorithms in the widely-used Morfessor software package.
Anthology ID:
2020.lrec-1.486
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
3944–3953
Language:
English
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.lrec-1.486/
DOI:
Bibkey:
Cite (ACL):
Stig-Arne Grönroos, Sami Virpioja, and Mikko Kurimo. 2020. Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3944–3953, Marseille, France. European Language Resources Association.
Cite (Informal):
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning (Grönroos et al., LREC 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.lrec-1.486.pdf
Code
 Waino/morfessor-emprune