From Parallel Grammar Development towards Machine Translation - A Project Overview -
نویسنده
چکیده
We give an overview of a MT research project jointly undertaken by Xerox PARC and XRCE Grenoble. The project builds on insights and resources in large-scale development of parallel LFG grammars. The research approach towards translation focuses on innovative computational technologies which lead to a flexible translation architecture. Efficient processing of "packed" ambiguities not only enables ambiguity preserving transfer. It is at the heart of a flexible architectural design, open for various extensions which take the right decisions at the right time.
منابع مشابه
Syntactic Analyses for Parallel Grammars: Auxiliaries and Genitive NPs
This paper focuses on two disparate aspects of German syntax from the perspective of parallel grammar development. As part of a cooperative project, we present an innovative approach to auxiliaries and multiple genitive NPs in German. The LFG-based implementation presented here avoids unnessary structural complexity in the representation of auxiliaries by challenging the traditional analysis of...
متن کاملTowards a shared task for shallow semantics-based translation (in an industrial setting)
In the Lingenio analysis systems, the sentences are analyzed into syntactic slot grammar representations from which so called 'dependency trees' are derived which reduce the analyses to the semantically relevant nodes and decorate these by information from the semantic lexicon. Slot grammar is a unification-‐based dependency grammar (cf. McCord 89). It has been used in the Logic based Machine ...
متن کاملDeep Grammars in a Tree Labeling Approach to Syntax-based Statistical Machine Translation
In this paper, we propose a new syntaxbased machine translation (MT) approach based on reducing the MT task to a treelabeling task, which is further decomposed into a sequence of simple decisions for which discriminative classifiers can be trained. The approach is very flexible and we believe that it is particularly well-suited for exploiting the linguistic knowledge encoded in deep grammars wh...
متن کاملSign Language Generation using HPSG
We discuss the problems of translating English to Sign Language in the ViSiCAST project. An overview of the language-processing component of an EnglishText to Sign-Languages translation system is described focusing upon the inherent problems of knowledge elicitation of sign language grammar and its implementation within a HPSG framework.
متن کاملMachine Translation of Film Subtitles from English to Spanish Combining a Statistical System with Rule - based Grammar
In this project we combined a statistical machine translation system for the translation of film subtitles from English to Spanish with rule-based grammar checking. At first we trained the best possible statistical machine translation system with the available training data. The largest part of the training corpus consists of freely available amateur subtitles. A smaller part are professionally...
متن کامل