Third Workshop on Computational Approaches to Arabic Script-based Languages |
Machine Translation Summit XII
|
Ottawa, Ontario, Canada|
Other papers (Included in the Proceedings) Syntactic generation of Arabic in Interlingua-based machine translation framework Khaled Shaalan (British University in Dubai) Arabic is a highly inflectional language, with
a rich morphology, relatively free word order,
and two types of sentences: nominal and verbal.
Arabic natural language processing in
general is still underdeveloped and Arabic
natural language generation (NLG) is even
less developed. In particular, Arabic natural
language generation from Interlingua was
only investigated using template-based approaches.
Moreover, tools used for other languages
are not easily adaptable to Arabic due
to the Arabic language complexity at both the
morphological and syntactic levels. In this
paper, we report our attempt at developing a
rule-based Arabic generator for task-oriented
interlingua-based spoken dialogues. Examples
of syntactic generation results from the
Arabic generator will be given and will illustrate
how the system works. Our proposed
syntactic generator has been effectively
evaluated using real test data and achieved
satisfactory results.
Disfluency and out-of-vocabulary word processing in Arabic speech understanding The disfluencies inherent in spontaneous speaking and out-of-vocabulary words omnipresent in any transcribed oral utterance by speech recognition, are a real challenge for speech understanding systems. Thus, we propose in this paper, a method for processing disfluencies and out-ofvocabulary words in the context of automatic Arabic speech understanding. Our method based on a robust and partial analysis of Arabic oral utterances (conceptual segments analysis) is effective for the treatment of such phenomena. This method has been tested through the understanding module of SARF system, an interactive vocal server for Tunisian railway information. Thus, the evaluation results are encouraging seeing that we obtained a decrease in error rate by 5.91%.
|
         |