I13-1137.pdf (241.43 kB)
Induction of root and pattern lexicon for unsupervised morphological analysis of Arabic
presentation
posted on 2023-06-08, 20:35 authored by Bilal Khaliq, John CarrollWe propose an unsupervised approach to learning non-concatenative morphology, which we apply to induce a lexicon of Arabic roots and pattern templates. The approach is based on the idea that roots and patterns may be revealed through mutually recursive scoring based on hypothesized pattern and root frequencies. After a further iterative refinement stage, morphological analysis with the induced lexicon achieves a root identification accuracy of over 94%. Our approach differs from previous work on unsupervised learning of Arabic morphology in that it is applicable to naturally-written, unvowelled text.
History
Publication status
- Published
Publisher URL
Page range
1012-1016Presentation Type
- paper
Event name
6th international joint conference on natural language processing (IJCNLP)Event location
Nagoya, JapanEvent type
conferenceEvent date
14-18 October 2013Department affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2015-04-24Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC