zunia.vn

Tuyển sinh 2024 dành cho Gen-Z

zunia.vn

» Luận Văn - Báo Cáo

» Báo cáo khoa học

Báo cáo khoa học: "Mechanical Translation Research at MIT"

Chia sẻ: Nghetay_1 Nghetay_1 | Ngày: | Loại File: PDF | Số trang:0

Báo xấu

50
lượt xem 1
download

Download Vui lòng tải xuống để xem tài liệu đầy đủ

WORK IN THE FIELD of mechanical translation started at MIT in 1951 when Y. Bar-Hillel became perhaps the first full-time worker in the field. In 1952, he organized the first international conference on mechanical translation. It, too, took place at MIT.

Chủ đề:

Bình luận(0) Đăng nhập để gửi bình luận!

Lưu

Nội dung Text: Báo cáo khoa học: "Mechanical Translation Research at MIT"

[Mechanical Translation, vol.3, no.2, November 1956; pp. 44-45] M echanical Translation Research at MIT † Victor H. Yngve. Massachusetts Institute of Technology, Cambridge, Massachusetts with sentence structure. These very difficult WORK IN THE FIELD of mechanical translation multiple-meaning problems can be resolved by started at MIT in 1951 when Y. Bar-Hillel be- machine routines based on the same sentence came perhaps the first full-time worker in the structure analysis that the machine would make field. In 1952, he organized the first interna- in order to initiate the word order changes. tional conference on mechanical translation. It, Examples of the sort of choices of meaning too, took place at MIT. Compared to this se- that could be made on the basis of sentence cond conference, the first one was small. We structure are not at all hard to find. Take, for have contributions from over thirty people at example,the word "der". Various meanings this conference compared to thirteen four years a re'the', 'of the', 'who', 'that', 'which', 'he', ago — striking evidence of how fast the field is 'it'. If the sentence structure is known, then growing. it is known whether "der" is an article, rela- B ar-Hillel was interested in syntactic tive pronoun, etc., and many, if not all, of the questions and was one of the foremost early ex- incorrect meanings can be eliminated. Each ponents of the point of view that a machine would of the other parts of speech offers many more have to handle syntactic problems in order to examples. provide adequate translations. Much of the An alternative to the use of rules based on work at MIT has continued from this point of sentence structure is the use of what may be view. The rather considerable difference in called ad hoc rules. For example, if "der" word order between German and English sen- follows a word that is capitalized without an tences indicates that a translation on a word- intervening comma, the translation 'of the' will for-word basis without word order change would be right about 95 per cent of the time. But it not be desirable. will be wrong in those very cases in which the Word order change, from German to English ad hoc rule does not correspond to the facts of a t least, often turns out to be phrase order sentence structure. The difficulty with ad hoc change. For example, the order of adverbial rules does not end with this 5-per-cent error; expressions (phrases) of time and place fre- many times it is virtually impossible to find quently has to be reversed, or they have to be any satisfactory ad hoc rule for a situation placed differently with respect to various ob- that is quite clear on a structural basis. jects or prepositional phrases. Routines for In the course of our work, one thing has making such word order changes would seem become very clear. If the machine is to recog- to require some mechanical procedure for se- nize the sentence structure, we must have a parating the sentence into phrases and clauses description of sentence structure to serve as a and identifying each of them as to kind or type. basis for the recognition routine. Some sort In other words, a machine routine for changing of a description is required for any recognition word order from German to English could be routine. Even ad hoc rules are based on a based on a routine for recognizing German sen- description — not a proper description of sen- tence structure. tence structure, but a description of certain Besides word order changes, the correct statistical features of a sample text and its meanings of the words must be selected. Many translations, such as: "In 95 per cent of the suggestions have been proposed for choosing cases where 'der' should be translated by 'of among the various possible meanings of words. the', 'der' is preceded, without an intervening The method that we are exploring in detail pro- comma, by a capitalized word." A few simple mises to solve some of the multiple-meaning ad hoc rules can provide a rough translation problems; namely, those that are connected that is better than a word-for-word translation, but the addition of more and more ad hoc rules is not the way to better and better translations, † This work was supported in part by the U.S. because these rules will become very involved Army (Signal Corps), the U.S. Air Force (Office and entangled one with another. A straight- of Scientific Research, Air Research and Deve- forward description of sentence structure may lopment Command), and the U.S. Navy (Office provide much simpler routines , and routines of Naval Research); and in part by the National that will handle problems that ad hoc rules Science Foundation.
MT Research 45 G.H. Matthews, in the short time that they can't handle. have been with the project, have looked into the In spite of the wealth of material on German structure of the German verb phrase, and the grammar and syntax, we have been unable to range of applicability of certain recognition find an adequate description of the language on rules of the type proposed by Oswald and which recognition routines could be based. And Fletcher. this for perhaps two reasons: In the first place, It is hoped that our work will lead to an ade- there has probably been no pressing need prior quate description of the German and English to MT for such a grammar and syntax. In the languages and thus to accurate syntactic trans- second place, perhaps linguists have not known lations with the proper choice of word order how to make such a grammar, or how to tell a and constructions in English from a German good grammar from a bad one. input. Many multiple-meaning problems will It is these problems that have been occupying be solved at the same time. There will still N. Chomsky. He has been working on a theory be problems left, however. These are connect- of grammar that gives many new and powerful ed with the so-called meaning words. Perhaps insights into the structure of language. these problems can be solved by utilizing a J. Applegate has been working on the detailed more sophisticated classification of the mean- structure of the German noun phrase. His ing of words than one has with a series of field descriptive statements will take their place in glossaries. a complete grammar of German. R. Lees and

CÓ THỂ BẠN MUỐN DOWNLOAD

LV.26: Bộ 320 Luận Văn Thạc Sĩ Y Học

320 tài liệu

1236 lượt tải

THÔNG TIN

TRỢ GIÚP

HỖ TRỢ KHÁCH HÀNG

Theo dõi chúng tôi

Chịu trách nhiệm nội dung:

Nguyễn Công Hà - Giám đốc Công ty TNHH TÀI LIỆU TRỰC TUYẾN VI NA

LIÊN HỆ

Địa chỉ: P402, 54A Nơ Trang Long, Phường 14, Q.Bình Thạnh, TP.HCM

Hotline: 093 303 0098

Email: support@tailieu.vn

Giấy phép Mạng Xã Hội số: 670/GP-BTTTT cấp ngày 30/11/2015 Copyright © 2022-2032 TaiLieu.VN. All rights reserved.