ArabTAG: from a Handcrafted to a Semi-automatically Generated TAG
نویسندگان
چکیده
In this paper, we present the redesign of an existing TAG for Arabic using a description language (so-called metagrammatical language). The use of such a language makes it easier for the linguist to share information among grammatical structures while ensuring a high degree of modular-ity within the target grammar. Additionally , this redesign benefits from a grammar testing environment which is used to check both grammar coverage and over-generation.
منابع مشابه
ArabTAG: a Tree Adjoining Grammar for Arabic Syntactic Structures
In order to construct a generic grammatical resource for Arabic language, we have chosen to develop an Arabic grammar based on TAG formalism. Our choice is, especially, justified by complementarities that we have noticed between Arabic syntax and this grammatical formalism. This paper consists of two comparative studies. The first is between a set of unification grammars. The second is between ...
متن کاملTags Re-ranking Using Multi-level Features in Automatic Image Annotation
Automatic image annotation is a process in which computer systems automatically assign the textual tags related with visual content to a query image. In most cases, inappropriate tags generated by the users as well as the images without any tags among the challenges available in this field have a negative effect on the query's result. In this paper, a new method is presented for automatic image...
متن کاملSurface Realisation from Knowledge-Bases
We present a simple, data-driven approach to generation from knowledge bases (KB). A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar); and that it takes into account both syntactic and semantic information. The resulting extracted TAG includes a unification based semantics and can be used by an existing...
متن کاملتصحیح خودکار خطا در درخت بانک نحوی با استفاده از یادگیری ماشینی انتقال محور
The Treebank is one of the most useful resources for supervised or semi-supervised learning in many NLP tasks such as speech recognition, spoken language systems, parsing and machine translation. Treebank can be developded in different ways that could be, generally, categorized in manually and statistical approaches. While the resulted Treebank in each of these methods has the annotation error,...
متن کاملAutomatic generation of weather forecast texts using comprehensive probabilistic generation-space models
Two important recent trends in nlg are (i) probabilistic techniques and (ii) comprehensive approaches that move away from traditional strictly modular and sequential models. This paper reports experiments in which pcru — a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space — was used to semi-automatically create five differ...
متن کامل