Machine Translation (Questionnaire 3)

2009/05/02

Machine Translation is the utilization of computers to the assignment of translating a text from a natural language, to another one. MT is one of the earliest researches in computer science. It has demonstrated to be a fleeting goal. Nowadays there are many systems which produce results with enough quality to be useful in so many specific fields.

At its simple grade, Machine translation makes simple exchanges of words in a natural language for word in another. Otherwise, with corpus techniques, the translation will be more complex.

Definition from the European Association for Machine Translation: “an organization that serves the growing community of people interested in MT and translation tools, including users, developers, and researchers of this increasingly viable technology”.

There are many types of Machine Translation:  Rule-based machine translation, Statistical machine translation and finally, Example-based machine translation.

  1. RULE-BASED MACHINE TRANSLATION:

At this kind of machine translation we can find: transfer-based machine translation, interlingual machine translation and finally, dictionary-based machine translation.

  1. STATISTICAL:

This one makes translations using statistical methods which are based on bilingual text corpora. For example: Canadian Hansard corpus, the English-French record of the Canadian parliament and EUROPARL, the record of the European Parliament.

  1. EXAMPLE-BASED:

This last one, is mainly a translation which is made by analogy. It can be considered as a use of case-based reasoning, which is an approximation to machine learning.

To end up with this article, I also have to mention some online automatic translators:

  • OpenTrad
  • Systran
  • ProMT
  • Lucy
  • Google Traductor
  • Translated
  • WorldLingo

 REFERENCES:

Entry Filed under: HLT. Tags: , , , , , , .

1 Comment Add your own

  • 1. Jim Goldman  |  2009/05/06 at 1:08 pm

    Machine translation can still not replace human translators for most needs. However, using it together with human translation might make translation much more efficient.

    Reply

Leave a Comment

Required

Required, hidden

Some HTML allowed:
<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <pre> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Trackback this post  |  Subscribe to the comments via RSS Feed


Sailak

Recent Posts

Artxibo

Blogroll

Lagunak

 

Maiatza 2009
M T W T F S S
« Apr   Jun »
 123
45678910
11121314151617
18192021222324
25262728293031

Tags

ANSI Artificial Intelligence BMW Bruce Springsteen Conference Cunningham Daimler Chrysler DKFI Eutanasia FeedRoll Gorputz Grishman Hans Uszkoreit HLT HTML Hypertext ISO Jay David Bolter Kevin Kevin Kelly Mar adentro Martin Kay Microsoft Named Entity Recognition OpenTrad Peshkin and Pheffer Platon Ramon Sampedro Relationship Extraction Riloff RSS RSS feeds RSS readers SAP SGML Systran Terminology extraction the E Street Band Walter G. Olthoff Walter Ong Wolfgang Wahlster Working on a dream XML Yangarber Yorick Wilks

Feeds

RSS litterako jarioa

RSS amaiaren bloga

Meta

RSS CiteUlike

RSS Google Books