By W. John Hutchins, Harold L. Somers

The interpretation of international language texts by means of pcs was once one of many first projects that the pioneers of computing and synthetic intelligence set themselves. computer translation is back turning into an incredible box of analysis and improvement because the want for translations of technical and advertisement documentation is transforming into well past the means of the interpretation career. this is often the 1st textbook of desktop translation, delivering an entire path on either basic laptop translation structures features and the computational linguistic foundations of the sector. laptop Translation assumes no earlier wisdom of the sphere and offers the fundamental history details to the linguistic and computational foundations of the topic. it truly is a useful textual content for college students of computational linguistics, synthetic intelligence, usual language processing, and knowledge technology.

Show description

Read Online or Download An Introduction to Machine Translation PDF

Similar intelligence & semantics books

Classical and Evolutionary Algorithms in the Optimization fo Optical Systems

The optimization of optical platforms is a really previous challenge. once lens designers came upon the potential for designing optical structures, the need to enhance these structures through the technique of optimization started. for a very long time the optimization of optical structures was once hooked up with recognized mathematical theories of optimization which gave stable effects, yet required lens designers to have a robust wisdom approximately optimized optical platforms.

Artificial neural networks and statistical pattern recognition : old and new connections

With the starting to be complexity of development acceptance similar difficulties being solved utilizing synthetic Neural Networks, many ANN researchers are grappling with layout concerns resembling the scale of the community, the variety of education styles, and function evaluate and limits. those researchers are consistently rediscovering that many studying approaches lack the scaling estate; the methods easily fail, or yield unsatisfactory effects while utilized to difficulties of larger dimension.

Non-Standard Parameter Adaptation for Exploratory Data Analysis

Exploratory information research, often referred to as facts mining or wisdom discovery from databases, is sometimes in keeping with the optimisation of a selected functionality of a dataset. Such optimisation is usually played with gradient descent or diversifications thereof. during this e-book, we first lay the foundation by means of reviewing a few usual clustering algorithms and projection algorithms ahead of featuring a number of non-standard standards for clustering.

Physical Computation and Cognitive Science

This publication offers a learn of electronic computation in modern cognitive technology. electronic computation is a hugely ambiguous notion, as there isn't any universal center definition for it in cognitive technology. considering the fact that this idea performs a significant position in cognitive conception, an enough cognitive clarification calls for an specific account of electronic computation.

Additional info for An Introduction to Machine Translation

Example text

Sentence (17b) seems acceptable, with the cataphoric reference of it to car, but in (17c) we cannot be sure if he refers to the old man or to some other person. Representations 21 (17a) It was very rough when we took the ferry from Liverpool to Dublin. (17b) You can put it in the garage if you come by car. (17c) He looked relieved when the old man heard he didn't have to pay tax. In general, the sequence of words and ideas in sentences is determined by text relationships. The start of a sentence typically makes a link to previous sentences; the initial words refer to elements already mentioned or presumed to be already known — either by anaphoric reference or by presupposition.

39b) John promised Mary to visit his father. 32 Linguistic background We know that in (39a) the person who is (or was) to visit John's father is not John but Mary, whereas in (39b) it is not Mary but John. The deep structure for (39a) would be (40). The derivation of the surface form (39a) from the deep structure in (40) involves the deletion of the NP Mary in the complement S, and the transformation of the finite verb (visit) into an infinitive. A similar deep structure for (39b) — with promised instead of persuaded and John instead of the second Mary — would involve the same rules to generate a surface form.

A CFG consists of a set of rewrite rules of the form A → α, where A belongs to a set of non-terminal symbols and α is a sequence of non-terminal and/or terminal symbols. The application of a sequence of rewrite rules is said to generate a representation of a sentence, and a grammar consisting of such rewrite rules is Formal grammar and linguistic theory 29 called a generative grammar. As we said above, we must be aware of the special meaning of the term ‘generate’ in this context. What a CFG grammar does is to define a formal relationship between a set of possible texts and their representations.

Download PDF sample

Rated 4.10 of 5 – based on 10 votes