Controlled language in machine translation: Difference between revisions

Revision as of 13:16, 23 February 2015

Latest revision as of 20:27, 19 July 2022

(6 intermediate revisions by 6 users not shown)

Line 1:

{{short description|Controlled natural language may simplify translation into another language.}}

{{nomore footnotes|date=February 2013}}

Using '''[[controlled language]] in [[machine translation]]''' poses several problems.

In an automated translation, the first step in order to understand the controlled language is to know what it is and to distinguish between [[natural language]] and [[controlled language]].

The main problem in [[machine translation]] is a linguistic problem. Language is ambiguous and the system tries to model a [[language]] on lexical and grammatical way. In order to solve this problem there are a lot of alternatives, e.g. a [[glossary]] related with the text’s topic can be used.

== A controlled language with ten rules ==

Grammar rules are different for each language. Because of this, the rules for controlled languages are different from one language to another. And there are no rules that have optimal results for all languages. There are however rules which reduce ambiguities in most texts in many languages. By Muegge{{who|date=June 2011}} and according to CLOUT ([[Controlled Language Optimized for Uniform Translation]]) the following ten rules should be applied:{{cn|date=June 2011}}

# Write sentences that are shorter than 25 words.

#*Be brief ( well structured)

#*Avoid ambiguity and subordination

#*Evaluate the information

#Write sentences that express only one idea.

#*Simple sentences

#*Avoid ( gerunds, juxtaposition, etc.)

#Write the same sentence if you want to express the same content.

#*Don’t be afraid to repeat

#*Avoid synonyms

#Write sentences that are grammatically complete.

#*Sentences grammatically and Orthographic correct

#*Avoid ellipsis.

#Write sentences that have a simple grammatical structure.

#*Avoid Juxtapostion, subordination, relatives pronouns, etc.

#Write sentences in the active form.

#*Avoid passive voice

#Write sentences that repeat the noun instead of using a pronoun.

#*Avoid pronouns like ''it'', ''their'', etc.

#Write sentences that use articles to identify nouns.

#*Use ''the'', ''this'', etc.

#Write sentences that use words from a general dictionary.

#*Do not use technical words

#Write sentences that use only words with correct spelling.

#*Avoid mistakes

== Benefits of using a controlled language ==

Line 44 ⟶ 16:

== Controlled language and translation==

One of the biggest challenges facing organizations that wish to reduce the cost and time involved in their translations is the fact that even in environments that combine content management systems with translation memory technology, the percentage of un-translated segments per new document remains fairly high. While it is certainly possible to manage content on the sentence/segment level, the current best practice seems to be to chunk at the topic level. Which means that reuse occurs at a fairly high level of granularity.

== References ==

{{Reflist}}

==Sources==

*AMORES CARREDANO, Jose Javier. Automatic translation systems[on line]. Available in: http://quark.prbb.org/19/019046.htm [Date of view: 29 May 2011]

Line 53 ⟶ 26:

*Grimaila, A.; Chandioux, J.: "Made to measure solutions". In: John Newton, ed.: ''Computers in Translation: A Practical Appraisal'', Londres, Routledge, 1992: 33-45.

*Hartley, A.F.; Paris, C.L.: «Multi-lingual document production: from support for translating to support for authoring», Machine Translation (Special Issue on new tools for human translators) 1997; 12 (12): 109-129.

*Ide, I; Véronis, J.: [https://aclanthology.org/J98-1001.pdf «Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art»], Computational Linguistics 1998; 24 (1): 1-40.

*Lehrberger, L.; Bourbeau, L.: Machine Translation: Linguistic Characteristics of [[machine translation]] Systems and General Methodology of Evaluation, Amsterdam/Filadelfia, John Benjamins, 1988.

Line 63 ⟶ 36:

[[Category:Translation]]

[[Category:Controlled natural languages]]

[[de:Übersetzungsgerechtes Schreiben]]