Keywords

Probabilistic Morphological Analyzer, Syriac Language, Data-driven Approach

Abstract

We define a probabilistic morphological analyzer using a data-driven approach for Syriac in order to facilitate the creation of an annotated corpus. Syriac is an under-resourced Semitic language for which there are no available language tools such as morphological analyzers. We introduce novel probabilistic models for segmentation, dictionary linkage, and morphological tagging and connect them in a pipeline to create a probabilistic morphological analyzer requiring only labeled data. We explore the performance of models with varying amounts of training data and find that with about 34,500 labeled tokens, we can outperform a reasonable baseline trained on over 99,000 tokens and achieve an accuracy of just over 80%. When trained on all available training data, our joint model achieves 86.47% accuracy, a 29.7% reduction in error rate over the baseline.

Original Publication Citation

A Probabilistic Morphological Analyzer for Syriac; 2010 Conference on Empirical Methods in NaturalLanguage Processing (EMNLP); MIT, Massachusetts; October 2010. [co-authors: Peter McClanahan,George Busby, Robbie Haertel, Kristian Heal, Kevin Seppi and Eric Ringger].

Document Type

Conference Paper

Publication Date

2010

Publisher

Association for Computational Linguistics

Language

English

College

Humanities

Department

Linguistics and English Language

University Standing at Time of Publication

Associate Professor

Download

Included in

Linguistics Commons

Share

COinS