Morphology-aware statistical machine translation based on morphs induced in an unsupervised manner

103 citations recorded by the source corpus.

How researchers see this paper

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

On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, methodology): “Word segmentation may also be helpful even when it does not strictly correspond to meaningful units (morphemes), as shown by unsupervised methods for obtaining sub-word units [108, 304, 315, 329, 344].”
Morfessor 2.0: Python Implementation and Extensions for Morfessor Baseline (2013, background): “…al., 2006; Creutz et al., 2007; Mihajlik et al., 2010; Gelas et al., 2012), speech retrieval (e.g. Arisoy et al., 2009; Turunen and Kurimo, 2011), and statistical machine translation (e.g. Virpioja et al., 2007; Luong et al., 2010; Mermer and Akın, 2010; Clifton and Sarkar, 2011; Popović, 2011).”
South-East European Times : A parallel corpus of Balkan languages , Francis Tyers and (2010, background): “51 Also, as noted by Virpioja et al. (2007), in morphologically rich languages words include more information on average, and one mistake in a suffix is enough to mark the whole word as incorrect, although it may not prevent understanding.”
Unsupervised Morphology Rivals Supervised Morphology for Arabic MT (2012, methodology): “A number of recent approaches have explored the use of unsupervised morphological analyzers for MT (Virpioja et al., 2007; Creutz and Lagus, 2007; Clifton and Sarkar, 2011; Mermer and Akın, 2010; Mermer and Saraclar, 2011).”