词条 | Rule-based machine translation |
释义 |
Rule-based machine translation (RBMT; "Classical Approach" of MT) is machine translation systems based on linguistic information about source and target languages basically retrieved from (unilingual, bilingual or multilingual) dictionaries and grammars covering the main semantic, morphological, and syntactic regularities of each language respectively. Having input sentences (in some source language), an RBMT system generates them to output sentences (in some target language) on the basis of morphological, syntactic, and semantic analysis of both the source and the target languages involved in a concrete translation task. HistoryThe first RBMT systems were developed in the early 1970s. The most important steps of this evolution were the emergence of the following RBMT systems:
Today, other common RBMT systems include:
Types of RBMTThere are three different types of rule-based machine translation systems:
RBMT systems can also be characterized as the systems opposite to Example-based Systems of Machine Translation (Example Based Machine Translation), whereas Hybrid Machine Translations Systems make use of many principles derived from RBMT. Basic principlesThe main approach of RBMT systems is based on linking the structure of the given input sentence with the structure of the demanded output sentence, necessarily preserving their unique meaning. The following example can illustrate the general frame of RBMT: A girl eats an apple. Source Language = English; Demanded Target Language = German Minimally, to get a German translation of this English sentence one needs:
And finally, we need rules according to which one can relate these two structures together. Accordingly, we can state the following stages of translation: 1st: getting basic part-of-speech information of each source word: a = indef.article; girl = noun; eats = verb; an = indef.article; apple = noun 2nd: getting syntactic information about the verb “to eat”: NP-eat-NP; here: eat – Present Simple, 3rd Person Singular, Active Voice 3rd: parsing the source sentence: (NP an apple) = the object of eat Often only partial parsing is sufficient to get to the syntactic structure of the source sentence and to map it onto the structure of the target sentence. 4th: translate English words into German a (category = indef.article) => ein (category = indef.article) girl (category = noun) => Mädchen (category = noun) eat (category = verb) => essen (category = verb) an (category = indef. article) => ein (category = indef.article) apple (category = noun) => Apfel (category = noun) 5th: Mapping dictionary entries into appropriate inflected forms (final generation): A girl eats an apple. => Ein Mädchen isst einen Apfel. ComponentsThe RBMT system contains:
a SL dictionary - needed by the source language morphological analyser for morphological analysis, a bilingual dictionary - used by the translator to translate source language words into target language words, a TL dictionary - needed by the target language morphological generator to generate target language words.[3] The RBMT system makes use of the following:
Advantages
Shortcomings
References1. ^{{cite book |title=Statistical Machine Translation |last=Koehn |first=Philipp |year=2010 |publisher=Cambridge University Press |location=Cambridge |page=15|url=https://books.google.com/books?id=4v_Cx1wIMLkC&printsec=frontcover#v=onepage&q=%22rule-based%22&f=false|isbn=9780521874151 }} 2. ^{{cite journal | jstor = 10.2307/40008396 | title = Knowledge-Based Machine Translation | last = Nirenburg | first = Sergei |year = 1989 | journal = Machine Trandation 4 (1989), 5 - 24 | volume = 4 | issue = 1 | pages = 5–24 | publisher = Kluwer Academic Publishers }} 3. ^{{cite web | url = http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6075022 | title = Computational Model of Grammar for English to Sinhala Machine Translation | last1 = Hettige | first1 = B. | last2 = Karunananda | first2 = A.S. |year = 2011 | work = The International Conference on Advances in ICT for Emerging Regions - ICTer20 11 : 026-031 | accessdate = 20 June 2012 }} 4. ^{{cite web | url = http://www.springerlink.com/content/v51w13n70m145786/fulltext.pdf | title = Acquisition of Large Lexicons for Practical Knowledge-Based MT | last1 = Lonsdale | first1 = Deryle | last2 = Mitamura | first2 = Teruko | last3 = Nyberg | first3 = Eric |year = 1995 | work = Machine Translation 9: 251-283 | publisher = Kluwer Academic Publishers | accessdate = 20 June 2012 }} 5. ^{{cite web | url = http://www.aclweb.org/anthology/N/N09/N09-2055.pdf | title = Statistical Post-Editing of a Rule-Based Machine Translation System | last1 = Lagarda | first1 = A.-L. | last2 = Alabau | first2 = V. | last3 = Casacuberta | first3 = F. | last4 = Silva | first4 = R. | last5 = Díaz-de-Liaño | first5 = E. | year = 2009 | work = Proceedings of NAACL HLT 2009: Short Papers, pages 217–220, Boulder, Colorado |publisher = Association for Computational Linguistics | accessdate = 20 June 2012 }} Literature
Links
2 : Machine translation|Natural language processing |
随便看 |
|
开放百科全书收录14589846条英语、德语、日语等多语种百科知识,基本涵盖了大多数领域的百科知识,是一部内容自由、开放的电子版国际百科全书。