An Introduction to Machine Translation by W. John Hutchins, Harold L. Somers

By W. John Hutchins, Harold L. Somers

The interpretation of international language texts by means of pcs used to be one of many first projects that the pioneers of computing and synthetic intelligence set themselves. computing device translation is back turning into a major box of analysis and improvement because the desire for translations of technical and advertisement documentation is turning out to be way past the potential of the interpretation occupation. this can be the 1st textbook of laptop translation, delivering an entire path on either basic computing device translation platforms features and the computational linguistic foundations of the sector. laptop Translation assumes no past wisdom of the sector and offers the elemental historical past info to the linguistic and computational foundations of the topic. it really is a useful textual content for college students of computational linguistics, synthetic intelligence, normal language processing, and data technology.

Show description

Read Online or Download An Introduction to Machine Translation PDF

Similar intelligence & semantics books

Communicating Process Architectures 2007: WoTUG-30

This book bargains with desktop technology and types of Concurrency. It rather emphasises on hardware/software co-design, and the certainty of concurrency that effects from those platforms. a variety of papers in this subject were integrated, from the formal modeling of buses in co-design structures via to software program simulation and improvement environments.

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems (The Springer International Series in Engineering and Computer Science)

Parsing potency is important while construction sensible traditional language platforms. 'Ibis is principally the case for interactive structures comparable to traditional language database entry, interfaces to specialist platforms and interactive computer translation. regardless of its value, parsing potency has bought little consciousness within the sector of average language processing.

Self-Evolvable Systems: Machine Learning in Social Media

This monograph offers key option to effectively deal with the becoming complexity of structures the place traditional engineering and clinical methodologies and applied sciences in accordance with studying and suppleness come to their limits and new methods are these days required. The transition from adaptable to evolvable and at last to self-evolvable platforms is highlighted, self-properties resembling self-organization, self-configuration, and self-repairing are brought and demanding situations and boundaries of the self-evolvable engineering platforms are evaluated.

Exploiting Linked Data and Knowledge Graphs in Large Organisations

This ebook addresses the subject of exploiting enterprise-linked information with a particularfocus on wisdom development and accessibility inside of organisations. It identifies the gaps among the necessities of firm wisdom intake and “standard”data eating applied sciences by way of analysing real-world use situations, and proposes theenterprise wisdom graph to fill such gaps.

Additional resources for An Introduction to Machine Translation

Example text

3 Feature-based representations In several sections above we have mentioned additional features — syntactic and semantic — which play a part in linguistic representation. In general, features can be represented as attributes with corresponding values, and as such are often called ‘attribute-value pairs’. Features can be used to represent almost everything we have discussed so far: ‘category’ can be an attribute with values such as ‘noun’, ‘verb’, ‘noun phrase’, etc; grammatical features such as ‘gender’, ‘number’, ‘tense’ are all possible attributes, with the expected range of values; ‘surface function’ might have values such as ‘subject’, ‘modifier’ and so on, while there might be a parallel attribute ‘deep function’, with the same range of values.

G. the Spanish and English systems developed at the Pan-American Health Organization (Washington, DC), and the systems designed by the Smart Corporation for Citicorp, Ford, and the Canadian Department of Employment and Immigration. Many of the Systran installations Further reading 9 are tailor-made for particular organisations (Aérospatiale, Dornier, NATO, General Motors). Nearly all these operational systems depend heavily on post-editing to produce acceptable translations. But pre-editing is also widespread: in some systems, for instance, operators are required, when inputting text, to mark word boundaries or even indicate the scope of phrases and clauses.

We will return to this question below. However the distinction between deep and surface syntactic functions is one which is generally accepted and understood. 3 Predicate-argument structure Syntactic relationships within sentences may also be described in terms of predicate-argument structures. This term refers to the traditional division of propositions in logic into predicates and arguments. A sentence such as (5a) above corresponds to the proposition run (boy), where the predicate run has a single argument boy; a sentence such as (8a) corresponds to gave (man, book, girl), a proposition with three arguments.

Download PDF sample

Rated 4.92 of 5 – based on 12 votes