Morphological Segmentation Inside-Out
Ryan Cotterell, Arun Kumar, Hinrich Sch\"utze

TL;DR
This paper introduces a discriminative, joint model for hierarchical morphological segmentation that captures derivational structures and orthographic changes, supported by a new annotated English word treebank.
Contribution
It presents the first context-free, discriminative model for hierarchical morphological segmentation and provides an annotated treebank for future research.
Findings
First hierarchical morphological segmentation model
Jointly models orthographic changes and segmentation
Provides an annotated English word treebank
Abstract
Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the case of derivational morphology. In this work, we introduce a discriminative, joint model of morphological segmentation along with the orthographic changes that occur during word formation. To the best of our knowledge, this is the first attempt to approach discriminative segmentation with a context-free model. Additionally, we release an annotated treebank of 7454 English words with constituency parses, encouraging future research in this area.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Text and Document Classification Technologies
