Adaptor Grammars for Unsupervised Paradigm Clustering

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This work describes the Edinburgh submission to the SIGMORPHON 2021 Shared Task 2 on unsupervised morphological paradigm clustering. Given raw text input, the task was to assign each token to a cluster with other tokens from the same paradigm. We use Adaptor Grammar segmentations combined with frequency-based heuristics to predict paradigm clusters. Our system achieved the highest average F1 score across 9 test languages, placing first out of 15 submissions.
Original languageEnglish
Title of host publicationProceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
EditorsGarrett Nicolai, Kyle Gorman, Ryan Cotterell
Place of PublicationOnline
PublisherAssociation for Computational Linguistics
Pages82-89
Number of pages8
DOIs
Publication statusPublished - 1 Aug 2021
EventThe 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Online
Duration: 5 Aug 20215 Aug 2021
Conference number: 18
https://sigmorphon.github.io/workshops/2021/

Workshop

WorkshopThe 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
Abbreviated titleSIGMORPHON 2021
Period5/08/215/08/21
Internet address

Fingerprint

Dive into the research topics of 'Adaptor Grammars for Unsupervised Paradigm Clustering'. Together they form a unique fingerprint.

Cite this