1 code implementation • NAACL 2022 • Ramy Eskander, Cass Lowry, Sujay Khandagale, Judith Klavans, Maria Polinsky, Smaranda Muresan
Our results show that the stem-based approach improves the POS models for all the target languages, with an average relative error reduction of 10. 3% in accuracy per target language, and outperforms the word-based approach that operates on three-times more data for about two thirds of the language pairs we consider.
no code implementations • LREC 2020 • Esk, Ramy er, Francesca Callejas, Elizabeth Nichols, Judith Klavans, Smar Muresan, a
Computational morphological segmentation has been an active research topic for decades as it is beneficial for many natural language processing tasks.
no code implementations • WS 2019 • Esk, Ramy er, Judith Klavans, Smar Muresan, a
Polysynthetic languages pose a challenge for morphological analysis due to the root-morpheme complexity and to the word class {``}squish{''}.