Báo cáo khoa học: Stochastic Methods of Mechanical Translation

IT IS WELL KNOWN that Western languages are 50% redundant. Experiment shows that if an average person guesses the successive words in a completely unknown sentence he has to be told only half of them. Experiment shows that this also applies to guessing the successive word-ideas in a foreign language.
Nội dung trích xuất từ tài liệu:
Báo cáo khoa học: "Stochastic Methods of Mechanical Translation" [Mechanical Translation, vol.3, no.2, November 1956; pp. 38-39]Stochastic Methods of Mechanical TranslationGilbert W. King, International Telemeter Corp., Los Angeles, CaliforniaIT IS WELL KNOWN that Western languages parts of speech, and may occur with specializedare 50% redundant. Experiment shows that if meanings in different disciplines, and it is tritean average person guesses the successive words to remark that these are the factors which makein a completely unknown sentence he has to be mechanical translation hard.told only half of them. Experiment shows that Further, in each entry there is, if necessary,this also applies to guessing the successive a computing program which is to instruct theword-ideas in a foreign language. How can this data processor to carry out certain searchesfact be used in machine translation? and logical operations on the sentence. It is clear that the success of the human in In operation, each sentence is considered asachieving a probability of .50 in anticipating the a semantic unit. All the words in the sentencewords in a sentence is largely due to his expe- are looked up in the dictionary, and all therience and the real meanings of the words al- material in each entry is delivered to the highready discovered. One cannot yet profitably speed, relatively low capacity store of the datadiscuss a machine with these capabilities. How- processor. This information includes targetever, a machine translator has a much easier equivalent, grammar and programs. The dataproblem - it does not have to make a choice processor now works out the instructionsfrom the wide field of all possible words, but is given to it by the programs, on all the othergiven in fact the word in the foreign language, material - equivalents, grammar and syntaxand only has to select One from a few possible belonging to the sentence - all in its own tem-meanings. porary store. In machine translation the procedure has to With these facilities in mind, we may nowbe generalized from guessing merely the next examine some of the procedures that can beword. The machine may start anywhere in the mechanized to allow the machine to guess at asentence and skip around looking for clues. The sequence of words which constitute its bestprocedure for estimating the probabilities and estimate of the meaning of the sentence in theselecting the highest may be classified into foreign language.several types, depending on the type of hardware The simplest type of problem is the uncon-in the particular machine-translating system scious pun which a human may face in seeingto be used. a headline in a newspaper in his own language. It is appropriate to describe briefly the system He has to scan the text to find the topic dis-currently planned and under construction. The cussed, and then go back to select the appro-central feature is a high-density store. This priate meaning. This can be mechanized byultimately will have a capacity of one billion having the machine scan the text (in this casebits and a random access time of 20 milli- more than one sentence is involved), pick outseconds. Information from the store is de- the words with only one meaning and make alivered to a high-speed data processor. A text statistical count of the symbols indicating fieldreader supplies the input and a high-speed of knowledge, and thus guess at the field underprinter delivers the output. The store serves discussion. (The calculations may be elaborat-as a dictionary, which is quite different from ed to weight the words belonging to more thanan ordinary manual type. Basically, of course, one field.)the store contains the foreign words and their A second type of multiple-meaning problemequivalents. The capacity is so large, however, where the probability of correct selection canthat all inflections (paradigmatic forms) of each be increased substantially and can also be me-stem are entered separately, with appropriate chanized is the situation where a word hasequivalents. In addition, in each entry, identifi- different meanings when it is in differentcation symbols are to be found, telling which grammatical forms, e.g. the two common andpart of speech the word is, and in which field annoying French w ...