Machine Translation презентация

translate text or speech from one natural language to another (http://en.wikipedia.org/)
Use: translation of large amount of date in the shortest possible time
Standard documents
Instructions and manuals
Web sites, multilingual search
Reference information(addresses, recipes, etc.)
Aim: to understand the main contents of the document in a foreign language unknown to the user
NOT to be used instead of human translation !!!

information about each word
Dictionary based translation
example:

A girl eats an apple. (Eng.-Ger.)
stages of translation:
1st: getting basic part-of-speech information of each source word: a = ind.art.; girl = n.; eats = v.; an = ind.art.; apple = n.
2nd: getting syntactic information about the verb “to eat”: here: eat – Pr. Simple, 3rd Pers. Sing., Act. V.
3rd: parsing the source sentence:(an apple) = the object of eat
4th: translate English words into Germana (category = indef.article) => ein (category = indef.article)girl (category = noun) => Mädchen…
5th: finding appropriate inflected forms: A girl eats an apple. => Ein Mädchen isst einen Apfel.

of statistical models whose parameters are derived from the analysis of bilingual text corpora
Benefits
Better use of resources
More natural translations
No programmers or linguists* involved

Shortcomings
Corpus creation can be costly for users with limited resources.
The results are unexpected. Superficial fluency can be deceiving.
Statistical machine translation does not work well between languages that have significantly different word orders

вероятности зависят от объема и качества обучающего корпуса
Лингвистическая информация: разбиение на предложения, графематический анализ, морфология
При наличии корпуса простейшая система перевода может быть сделана на 2 недели

long lists of phrases on the subsentential (i.e., not a full sentence) level, e.g. lists, inventories or simple catalogs of products and services.

(and sometimes semantics)

2. Creating an internal representation

3. Generating translation using both bilingual dictionaries and grammatical rules

Sentence in a source language

Source language structure

Sentence in a target language

Target language structure

analysis

transfer

synthesis

an abstract language-independent representation
the target language is generated from the interlingua.

approaches within a single machine translation system.

Types:
RBMT guided by statistics
Statistical method guided by RBMT