Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Refine search results

Journals help

  1. 2 Neophilologica

Authors help

  1. 2 Śmigielska B.

Years help

  1. 1 2023

  2. 1 2020

Results found: 2

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  supervised automatic translation
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

Cadres, scripts, registres - complexité de traduction des mots polysémiques

100%
Śmigielska B.
Neophilologica
|
2020
|
vol. 32
348-368
EN
The article deals with issues related to the description of polysemic units for supervised automatic translation of texts from French to Polish based on the object-oriented method by W. Banyś (AOO). Applying to the description additional tools allowing for the disambiguation - frames, scripts and register analysis - the author focuses on presenting the complexity of the description of lexical units. It should be stressed that the decision to assign meanings of such words one or another equivalents in the target language is determined by the criterion of preference. Some of the meanings of the word are easy to describe in such a way that the program can make a correct translation into the target language with a high degree of probability. However, there are often such meanings whose description is much more complex. The closer the meanings of the disambiguated words in the original and target language and the more similar the communication situation in which they are used, the more difficult it is to clearly indicate the boundaries between the meanings. In such cases, there is a much greater range of preferential character of the translation, which we have to adopt The French noun conjunction (f), chosen for analysis, reflects this phenomenon very well.
2
Publication available in full text mode
Content available

Traduction automatique et désambiguïsation des sens des mots. Le cas du verbe français louer

100%
Śmigielska B.
Neophilologica
|
2023
|
vol. 35
1-26
EN
Machine translators such as those offered by Google, Deep, ChatGPT and others are already using NMT systems. They apply the techniques of artificial intelligence that are constantly being developed, so they are currently providing increasingly correct and suitable translations. In the first part of this article, the author examines the case of the French verb louer by having it translated in different contexts by three automatic translators mentioned to see how effective they currently are as translation tools. Next, the verb louer is presented and analyzed as seen through the prism of the Antidote 8 dictionary. The last part of the article is devoted to the French-Polish description of the verb studied using the Object-Oriented Approach, with the aim of disambiguating it and developing the system of syntactico-semantic rules (object classes, frames, scripts) enabling the appropriate automatic translation of sentences in which it may appear.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.