Coordination, incorporation and dynamic semantic representation in transfer
نویسنده
چکیده
Factorized coordinated predicative structures prove to be a problem to transfer whenever the bilingual lexicon suggests a non-isomorphic translation for one of the predicative conjuncts, in particular a solution that requires incorporation of the predicative description into the translation of the source (support) verb. The problem disappears if the factorized structure is ’multiplied out’, resulting in a structure where the coordination is raised to VP. Since many languages make use of such factorized coordinations and since, normally, one can translate them into each other, ’multiplying out’ is unnecessary in most of the cases and costly. We suggest a semantics based transfer architecture in this paper which, per default, avoids unfolding the factorized representation and makes it dependent on constraints formulated in the bilingual lexicon whether corresponding structural revision is needed. If so, triggered by such constraints, it is computed on the fly during transfer.
منابع مشابه
The Effect of Semantic Transfer on Iranian EFL Learners’ Lexical Representation and Processing
متن کامل
Interplay of reversible chain transfer and comonomer incorporation reactions in coordination copolymerization of ethylene/1–hexene
Coordinative chain transfer polymerization (CCTP) has opened a new path for the development of novel products like olefin block copolymers and chain-end functional polyolefins. However, conflicting results are frequently reported on the catalyst performance including activity and comonomer selectivity under CCTP conditions. Here we have selected two catalysts including rac-ethylenebis(1-η5-inde...
متن کاملImage Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کاملA Joint Semantic Vector Representation Model for Text Clustering and Classification
Text clustering and classification are two main tasks of text mining. Feature selection plays the key role in the quality of the clustering and classification results. Although word-based features such as term frequency-inverse document frequency (TF-IDF) vectors have been widely used in different applications, their shortcoming in capturing semantic concepts of text motivated researches to use...
متن کاملSemantic Tuple Space Coordination for the Semantic Web with Applications in Life Science
Semantic Tuple Space Coordination for the Semantic Web with Applications in Life Science Peishen Qi 2007 The primary goal of the Semantic Web is to provide a web of data that are accessible and processable by machines. Different communities have started to publish their resources using Resource Description Framework (RDF), RDF Schema (RDFS), or Web Ontology Language (OWL), based on the level of...
متن کامل