Kevin Seppi

4 paper cards in Mova's library · 2010–2014

Kevin Seppi wrote 4 of the papers Mova reads, in 2010–2014; often with Eric Ringger, Deryle Lonsdale, Kristian Heal.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Evaluating Lemmatization Models for Machine-Assisted Corpus-Dictionary Linkage (2014)
The task is to link each word token of a Syriac corpus to the right dictionary headword (corpus-dictionary linkage), here reduced to stem-to-baseform linkage, since segmentation already reaches about 98.9% accuracy.
First Results in a Study Evaluating Pre-annotation and Correction Propagation for Machine-Assisted Syriac Morphological Analysis (2012)
The authors ask when machine pre-annotation (the annotator corrects a machine guess instead of starting from nothing) and correction propagation (a correction re-runs the model on the rest of the same sentence) make Syriac morphological annotation faster and more accurate.
A Probabilistic Morphological Analyzer for Syriac (2010)
The authors build a data-driven morphological analyzer for Syriac, an unvocalized Aramaic dialect with no existing tools, which needs only labelled data.
CCASH: A Web Application Framework for Efficient, Distributed Language Resource Development (2010)
CCASH is a web application framework for corpus annotation, built so that cost-efficient methods such as active learning and automatic pre-labelling can first be tried in user studies and then run on large projects.