Portuguese-Chinese machine translation in Macao

17293

Authors

nan

Abstract

AbstractThere have been substantial changes in computing practices in the cyberspace, mainly as a result of the proliferation of low priced under-utilized powerfully heterogeneous computers are connected by high-speed links. In this paper we reminisce the vicissitude of computing platform and introduce our Portuguese-Chinese corpus-based machine translation (CBMT) system which employs a statistical approach with automatic bilingual alignment support. Our improved algorithm for aligning bilingual parallel texts can achieve 97% of accuracy. At the same time, we broach the "distributed translation computing" concept to construct a uniform distributed shared-object technical term retrieving workstation and achieve high computing performance balance of network where heterogeneous computers inherently root and are intermittently under-utilized. Whereby it, we can expedite to retrieve technical terms from noisy bilingual web text and build up the Portuguese-Chinese corpus-base.

Keywords

nan

Full Content

MT Summit VII Sept. 1999 Portuguese-Chinese Machine Translation in Macao Yiping Li Chiman Pun Fei Wu Faculty of Science and Faculty of Science and Faculty of Science and Technology Technology Technology University of Macao University of Macao University of Macao P.O.Box 3001, Macao P.O.Box 3001, Macao P.O.Box 3001, Macao Abstract There have been substantial changes in computing practices in the cyberspace, mainly as a result of the proliferation of low priced under-utilized powerfully heterogeneous computers are connected by high- speed links. In this paper we reminisce the vicissitude of computing platform and introduce our Portuguese- Chinese corpus-based machine translation (CBMT) system which employs a statistical approach with automatic bilingual alignment support. Our improved algorithm for aligning bilingual parallel texts can achieve 97% of accuracy. At the same time, we broach the "distributed translation computing" concept to construct a uniform distributed shared- object technical term retrieving workstation and achieve high computing performance balance of network where heterogeneous computers inherently root and are intermittently under-utilized. Whereby it, we can expedite to retrieve technical terms from noisy bilingual web text and build up the Portuguese- Chinese corpus-base. 1 The vicissitude of computing platforms Automatic translation between human languages ('Machine Translation') was one of the earliest tantalizing applications suggested for digital computers, but turning this dream into reality has turned out to be a much harder, and in many ways a much more interesting task than at first appeared. If machine translation could be regarded as the one of earliest complicated synthetic computation in cyberspace, then where the computing concept stems? Two thousand years ago, Euclid set a famous standard for rigor in geometrical proofs, which is called Completeness and Consistency now. In order to settle the standard initiated by Euclid, Logicians and mathematicians have to first conceive an effective computing platform to determine whether a given proposed inference is valid from the premises. There have ever been many examples of innovative concepts and computing platforms introduced by logicians and mathematicians which later proved to be important in current computer science, but all of those computing platforms are immanently confined to certain cases. In 1936 papers by Church, Kleene, Turing and Post were almost simultaneously published. Each of the authors proposed a precise definition for the seemingly vague notion of effective computing platform, namely recursive function (Godel- Herbrand, 1934), Lemada-Calculus (Church-Kleene, 1932-1934), Turing machine (Alan Turing 1936). According to Church thesis, all of computing platforms above can be shown to be equivalent. It is not uncommon in mathematics and in the other sciences for concepts, methods, and theorems to be discovered independently and almost at the same time. Why eventually Turing's work has proved to be of greatest mathematical and philosophical significance than that of the other authors and adumbrates the first powerful all- purpose digital computer? What Turing did was to show that calculation can be broken down into the iteration (controlled by an internal state program) of extremely simple concrete operations; the processes of calculation is so concrete that they can be …

Content truncated to 500 words

Labeled Text

AbstractThere have been substantial changes in computing practices in the cyberspace, mainly as a result of the proliferation of low priced under-utilized powerfully heterogeneous computers are connected by high-speed links. In this paper we reminisce the vicissitude of computing platform and introduce our Portuguese-Chinese corpus-based machine translation (CBMT) system which employs a statistical approach with automatic bilingual alignment support. Our improved algorithm for aligning bilingual parallel texts can achieve 97% of accuracy. At the same time, we broach the "distributed translation computing" concept to construct a uniform distributed shared-object technical term retrieving workstation and achieve high computing performance balance of network where heterogeneous computers inherently root and are intermittently under-utilized. Whereby it, we can expedite to retrieve technical terms from noisy bilingual web text and build up the Portuguese-Chinese corpus-base.

Publication Details

Paper ID:
17293
Year:
1999
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan