In this study, the aim is to propose a new method for fuzzification of nested dummy variables. The fuzzification idea of dummy variables has been acquired from non-linear part of regime switching models in econometrics. In these models, the concept of transfer functions is like the notion of fuzzy membership functions, but no principle or linguistic sentence have been used for inputs. Consequen...

This paper describes ongoing research on NLG for dialogue systems. Sentence planning is performed by selecting the appropriate template, while previously developed transfer and generation components of a transfer–based MT architecture perform the lexicalization and linguistic realization processes in the generation process. This approach allows for multilingual generation since there is a clear...

This paper concerns formal tools and methods for describing the transfer phase of a machine translation process. The unificational firameworic o f the MuITra formalism is elaborated. The transfer relation rqrresenting a relation between translation units is formally defined. A control structure based on qiecificity is introduced, and shown to provide a way o f treating some linguistic phenomena.

Transfer phenomena in Italian L3 by Dutch-speaking learners Consequences for didactics
 The present study investigates some aspects of the learning process as an two groups multilingual learners. In particular, through examination learners’ cross-linguistic transfer occurrences we reflect on didactic consequences working with mastering several L2s. results suggest that can be influenced an...

Text attribute transfer using non-parallel data requires methods that can perform disentanglement of content and linguistic attributes. In this work, we propose different improvements that enable the encode-decode framework to cope with text attribute transfer from non-parallel data. We perform experiments on the sentiment transfer task using two different datasets. For both datasets, our propo...

Parallel corpora encode extremely valuable linguistic knowledge, the revealing of which is facilitated by the recent advances in multilingual corpus linguistics. The linguistic decisions made by the human translators in order to faithfully convey the meaning of the source text can be traced and can bring evidence on linguistic facts which in a monolingual context might be overlooked by a comput...

Multilingual technologies, which to a large extent are language independent, provide a powerful support for easier building of annotated linguistic resources for languages where such resources are scarce or missing. All these technologies require parallel corpora in order to achieve their ends. Parallel texts encode extremely valuable linguistic knowledge because the linguistic decisions made b...