Labeled Morphological Segmentation with Semi-Markov Models

Abstract

We present labeled morphological segmentation, an alternative view of morphological processing that unifies several tasks. From an annotation standpoint, we additionally introduce a new hierarchy of morphotactic tagsets. Finally, we develop , a discriminative morphological segmentation system that, contrary to previous work, explicitly models morphotactics. We show that chipmunk yields improved performance on three tasks for all six languages: (i) morphological segmentation, (ii) stemming and (iii) morphological tag classification. On morphological segmentation, our method shows absolute improvements of 2--6 points F_1 over the baseline.

Tasks

Reproductions