Unsupervised Morpheme Segmentation and Morphology Induction from Text Corpora Using Morfessor 1.0

By Mathias Creutz, Krista Lagus. 2005

325 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2d6a97f83bb8207ea9d88118618ed3ab52054a88

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Unsupervised models for morpheme segmentation and morphology learning (2007, methodology): “User s instructions are provided in a technical report [Creutz and Lagus 2005b] which further describes the models and the search algorithm used.”
A Character-level Decoder without Explicit Segmentation for Neural Machine Translation (2016, methodology): “This problem is however a difficult problem on its own and often requires decades of research (see, e.g., Creutz and Lagus (2005) for Finnish and other morphologically rich languages and Huang and Zhao (2007) for Chinese).”
Byte Pair Encoding is Suboptimal for Language Model Pretraining (2020, methodology): “This mirrors the main ﬁndings of Creutz and Lagus (2005), who successfully use maximum-a-posteriori unigram language models to perform unsupervised morphological segmentation of English and Finnish.”
Automatic speech recognition for under-resourced languages: A survey (2014, methodology): “There are some widely used software for unsupervised word decomposition, for instance Morfessor (Creutz and Lagus, 2005) that was originally developed for Finnish.”
Morfessor 2.0: Python Implementation and Extensions for Morfessor Baseline (2013, methodology): “The standard training algorithm for Morfessor Baseline—described in detail also by Creutz and Lagus (2005b)—applies a recursive, greedy search.”
Developments of Swahili resources for an automatic speech recognition system (2012, methodology): “Concerning language modeling, the advantage of sub-unit improved performance for this morphologically rich language and can be performed without any specific knowledge through the application of unsupervised methods, for instance the publicly available tool Morfessor.”
Morphological Word-Embeddings (2019, methodology): “(2013) described a recursive neural network LM, whose topology was derived from the output of MORFESSOR, an unsupervised morphological segmentation tool (Creutz and Lagus, 2005).”
Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English (2017, methodology): “Another study tried to overcome this limitation by us-ing the Baseline variant of Morfessor (Creutz and Lagus, 2005b), which allows to reach a vocabulary size set prior to segmentation (Bradbury and Socher, 2016).”