A link grammar parser for Arabic

Casbeer, Warren; Dehdari, Jon; Lonsdale, Deryle

doi:10.1075/cilt.290.19cas

Cited by 3 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…‫احساس'‬ ‫ا‬ ‫ر‬ ‫درد‬ ‫او‬ ‫کند‬ ‫'می‬ [u daerd rɑ ehsɑs mi-konaed] 'he/she feels the pain' vs. ‫کند'‬ ‫می‬ ‫درد‬ ‫احساس‬ ‫'او‬ [u ehsɑs-e daerd mi-konaed] 'he/she feels the pain'), and cannot handle words containing copula (the enclitic form of the verb ‫'بودن'‬ [budaen] 'to be' in the present indicative) as in ‫'مشغولند'‬ [maeshqul-aend] '(they) are busy'. Dehdari and Lonsdale (2008) is a link grammar parser based on Sleator and Temperley (1991). Furthermore, Valad (2006) employs a unification-based approach to Persian grammar utilizing semantic features for Persian syntactic disambiguation.…”

Section: Related Workmentioning

confidence: 99%

An intelligent extension of the training set for the Persian n-gram language model: an enrichment algorithm

Motavallian,

Komeily

2023

Onomázein

View full text Add to dashboard Cite

In this article, we are going to introduce an automatic mechanism to intelligently extend the training set to improve the n-gram language model of Persian. Given the free word-order property in Persian, our enrichment algorithm diversifies n-gram combinations in baseline training data through dependency reordering, adding permissible sentences and filtering ungrammatical sentences using a hybrid empirical (heuristic) and linguistic approach. Experiments performed on baseline training set (taken from a standard Persian corpus) and the resulting enriched training set indicate a declining trend in average relative perplexity (between 34% to 73%) for informal/spoken vs. formal/written Persian test data.

show abstract

Section: Related Workmentioning

confidence: 99%