Morphological Disambiguation of Turkish Text with Perceptron Algorithm

108 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.

Improving Neural Machine Translation Models with Monolingual Data (2015, methodology): “Gülçehre et al. (2015) segment the Turkish text with the morphology tool Zemberek, followed by a disambiguation of the morphological analysis (Sak et al., 2007), and removal of non-surface to-kens produced by the analysis.”
Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English (2017, methodology): “We adopt the pre-processing approach of Bisazza and Federico (2009), who used the suﬃx combinatory ﬁnite-state analyzer of Oﬂazer (1994) to tag each sub-word unit in a Turkish word, and a morphological disambiguation tool (Sak et al., 2007) to decreasethe sparseness caused by suﬃx allomorphy.”
Yandex School of Data Analysis approach to English-Turkish translation at WMT16 News Translation Task (2016, methodology): “We used an in-house finite state transducer similar to (Oflazer, 1994) for Turkish morphological tagging, and structured perceptron similar to (Sak et al., 2007) for morphological disambiguation.”
Dense Information Flow for Neural Machine Translation (2018, methodology): “, 2015a), we use the morphology tool Zemberek with disambiguation by the morphological analysis (Sak et al., 2007) and removal of non-surface tokens2.”
TÜBİTAK SMT System Submission for WMT2016 (2016, methodology): “Then morphological disambiguation is performed on the morphological analyses (Sak et al., 2007).”