Explaining A Deep Learning Based Model for Spelling Correction of "de/da" Clitics in Turkish through Understanding Their Dependence to Various Regions of A Sentence

A model agnostic perturbation-based explanation approach is proposed for the spellchecker of Turkish “de/da” spelling errors.

avatar Alperen Değirmenci
avatar Hasan Öztürk
poster
Poster

A model agnostic perturbation-based explanation approach is proposed for the spellchecker of Turkish “de/da” spelling errors. Findings of this approach are validated with a GWAP application.

Poster: https://drive.google.com/file/d/153rHCPoiE9ekSgToMeVPrIxXfq4lDTPp/view?usp=sharing

Video: https://drive.google.com/file/d/1O0dBZo5igdgThW6UfE5y3tAO96htmxli/view?usp=sharing

Advisors

Suzan Üsküdarlı