Lexical Allocation in Interlingua-based Machine Translation of Spatial Expressions
نویسندگان
چکیده
Given a spatial expression, or its computational semantic form, how is the expression’s spatial semantics to be allocated lexically, i.e., among entries in the lexicon? In interlingua-based machine translation (MT) research, lexical allocation is the problem of allocating or subdividing a linguistic expression’s full interlingual (IL) structure into the substructures that are lexical IL forms, i.e., in the lexicon. Here we present our work developing IL forms and an IL lexicon for translating English spatial expressions into Turkish. We examine several co-occurrence patterns between motion verbs (spatial placement and displacement) and directional adpositions (particles in English, postpositions in Turkish) and the lexical allocation of spatial vectors in these patterns.
منابع مشابه
Machine Translation Strategies: A Comparison of F-Structure Transfer and Semantically Based Interlingua
Two machine translation (MT) systems which respectively utilize the transfer and interlingua strategies will be presented and compared, emphasizing design principles. Feature structures and unification-based grammar are common denominators for the two MT systems; in particular, both make use of Lexical-Functional Grammar (LFG). In the transfer system. Machine Translation Toolkit, developed by E...
متن کاملMachine Translation of Spatial Expressions: Defining the Relation between an Interlingua and a Knowledge Representation System
متن کامل
A Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملA Language-Independent System for Generating Feature Structures from Interlingua Representations
Two main problems in natural language generation are lexical selection and syntactic structure determination In interlingua approach to machine translation determining sentence structures becomes more di cult especially when the interlingua does not contain any syntactic information In this paper a knowledge based computational model which handles these two problems in interlingua approach is p...
متن کاملThe Case for a MT Developers' Tool with a Two-Component View of the Interlingua
The interlingua (IL) in machine translation (MT) systems can be defined in terms of two components: (i) "lexical IL forms" within language-specific lexicons where each lexical entry has associated with it one or more lexical representations, and (ii) algorithms for creating and decomposing the instantiated "pivot" representation. Within this framework, we examine five different approaches to th...
متن کامل