Syntactic Theory and Grammar Design for Machine Translation
نویسنده
چکیده
Recently, the field of machine translation has increasingly reflected the influence of linguistic theory. Some systems have been designed around principles or structures of specific theories (Dorr, 1989; Kaplan, Netter, Wedekind, & Zaenen, 1989; Sharp, 1986), whereas others, adhering less strongly to particular theories, nevertheless reflect great care in considering and adapting the work of linguists. Most notable in this respect is the EUROTRA project as described, for example, in Arnold & des Tombe (1987) and Durand et al. (to appear). There seems to be general agreement that linguistic theory can contribute to machine translation (Raskin, 1987a, 1987b; Wehrli, 1987), but at the same time there is skepticism about its potential to break the barriers to robust, high quality translation (Nagao et al., 1988). As a result, many questions remain about the place of linguistic theory in machine translation.
منابع مشابه
Syntactic Transformations Modelling for Hybrid Machine Translation
The paper deals with the problems of crosslanguage syntactic transformations modelling for design and development of transfer-based machine translation systems. The solutions are proposed on the basis of the hybrid grammar comprising linguistic rules and statistical information about the language structures preferred in particular languages.
متن کاملAmbiguity Resolution for Machine Translation of Telegraphic Messages
Telegraphic messages with numerous instances of omission pose a new challenge to parsing in that a sentence with omission causes a higher degree of ambi6uity than a sentence without omission. Misparsing reduced by omissions has a far-reaching consequence in machine translation. Namely, a misparse of the input often leads to a translation into the target language which has incoherent meaning in ...
متن کاملExtending CCG-based Syntactic Constraints in Hierarchical Phrase-Based SMT
In this paper, we describe two approaches to extending syntactic constraints in the Hierarchical Phrase-Based (HPB) Statistical Machine Translation (SMT) model using Combinatory Categorial Grammar (CCG). These extensions target the limitations of previous syntax-augmented HPB SMT systems which limit the coverage of the syntactic constraints applied. We present experiments on Arabic–English and ...
متن کاملFine-Grained Tree-to-String Translation Rule Extraction
Tree-to-string translation rules are widely used in linguistically syntax-based statistical machine translation systems. In this paper, we propose to use deep syntactic information for obtaining fine-grained translation rules. A head-driven phrase structure grammar (HPSG) parser is used to obtain the deep syntactic information, which includes a fine-grained description of the syntactic property...
متن کاملCCG Supertags in Factored Statistical Machine Translation
Combinatorial Categorial Grammar (CCG) supertags present phrase-based machine translation with an opportunity to access rich syntactic information at a word level. The challenge is incorporating this information into the translation process. Factored translation models allow the inclusion of supertags as a factor in the source or target language. We show that this results in an improvement in t...
متن کاملParsing Extended Constraint Synchronous Grammar in Chinese-Portuguese Machine Translation
This paper presents a design model for parsing an extended version of Constraint Synchronous Grammar (CSG) for Chinese-Portuguese MT, which was initially applied in the reverse way. CSG is a generalization of context free grammars that describes syntactic structures of two languages simultaneously based on the defined constraints. Extensions include the addition of part of speech information in...
متن کامل