Translation is the interpreting of the meaning of a text and the subsequent production of an equivalent text, likewise called a "translation," that communicates the same message in another language. The text to be translated is called the "source text," and the language that it is to be translated into is called the "target language"; the final product is sometimes called the "target text."
Translation must take into account constraints that include context, the rules of grammar of the two languages, their writing conventions, and their idioms. A common misconception is that there exists a simple word-for-word correspondence between any two languages, and that translation is a straightforward mechanical process; such a word-for-word translation, however, cannot take into account context, grammar, conventions, and idioms.
Translation is fraught with the potential for "spilling over" of idioms and usages from one language into the other, since both languages coexist within the translator's mind. Such spilling-over easily produces linguistic hybrids such as "Franglais" (French-English), "Spanglish" (Spanish-English), "Poglish" (Polish-English) and "Portuñol" (Portuguese-Spanish).
On the other hand, inter-linguistic spillages have also served the useful purpose of importing calques and loanwords from a source language into a target language that had previously lacked a concept or a convenient expression for the concept. Translators and interpreters, professional as well as amateur, have thus played an important role in the evolution of languages and cultures.
The art of translation is as old as written literature. Parts of the Sumerian Epic of Gilgamesh, among the oldest known literary works, have been found in translations into several Asiatic languages of the second millennium BCE. The Epic of Gilgamesh may have been read, in their own languages, by early authors of the Bible and of the Iliad.
With the advent of computers, attempts have been made to computerize or otherwise automate the translation of natural-language texts (machine translation) or to use computers as an aid to translation (computer-assisted translation).
Etymologically, "translation" is a "carrying across" or "bringing across." The Latin "translatio" derives from the perfect passive participle, "translatum," of "transferre" ("to transfer" — from "trans," "across" + "ferre," "to carry" or "to bring"). The modern Romance, Germanic and Slavic European languages have generally formed their own equivalent terms for this concept after the Latin model — after "transferre" or after the kindred "traducere" ("to bring across" or "to lead across").
Additionally, the Greek term for "translation," "metaphrasis" ("a speaking across"), has supplied English with "metaphrase" (a "literal translation," or "word-for-word" translation)—as contrasted with "paraphrase" ("a saying in other words," from the Greek "paraphrasis"). "Metaphrase" corresponds, in one of the more recent terminologies, to "formal equivalence," and "paraphrase", to "dynamic equivalence."
Newcomers to translation sometimes proceed as if translation were an exact science — as if consistent, one-to-one correlations existed between the words and phrases of different languages, rendering translations fixed and identically reproducible, much as in cryptography. Such novices may assume that all that is needed to translate a text is to "encode" and "decode" equivalents between the two languages, using a translation dictionary as the "codebook."
On the contrary, such a fixed relationship would only exist were a new language synthesized and simultaneously matched to a pre-existing language's scopes of meaning, etymologies, and lexical ecological niches.  If the new language were subsequently to take on a life apart from such cryptographic use, each word would spontaneously begin to assume new shades of meaning and cast off previous associations, thereby vitiating any such artificial synchronization. Henceforth translation would require the disciplines described in this article.
Another common misconception is that anyone who can speak a second language will make a good translator. In the translation community, it is generally accepted that the best translations are produced by persons who are translating into their own native languages, as it is rare for someone who has learned a second language to have total fluency in that language. A good translator understands the source language well, has specific experience in the subject matter of the text, and is a good writer in the target language. Moreover, he is not only bilingual but bicultural.
It has been debated whether translation is art or craft. Literary translators, such as Gregory Rabassa in If This Be Treason, argue that translation is an art – a teachable one. Other translators, mostly technical, commercial, and legal, regard their métier as a craft – again, a teachable one, subject to linguistic analysis, that benefits from academic study.
As with other human activities, the distinction between art and craft may be largely a matter of degree. Even a document which appears simple, e.g. a product brochure, requires a certain level of linguistic skill that goes beyond mere technical terminology. Any material used for marketing purposes reflects on the company that produces the product and the brochure. The best translations are obtained through the combined application of good technical-terminology skills and good writing skills.
Translation has served as a writing school for many prominent writers. Translators, including the early modern European translators of the Bible, in the course of their work have shaped the very languages into which they have translated. They have acted as bridges for conveying knowledge and ideas between cultures and civilizations. Along with ideas, they have imported, into their own languages, loanwords and calques of grammatical structures, idioms and vocabulary from the source languages.
See main article: Interpreting. Interpreting, or "interpretation," is the intellectual activity that consists of facilitating oral or sign-language communication, either simultaneously or consecutively, between two or among three or more speakers who are not speaking, or signing, the same language.
The words "interpreting" and "interpretation" both can be used to refer to this activity; the word "interpreting" is commonly used in the profession and in the translation-studies field to avoid confusion with other meanings of the word "interpretation."
Not all languages employ, as English does, two separate words to denote the activities of written and live-communication (oral or sign-language) translators. Even English does not always make the distinction, frequently using "translation" as a synonym of "interpretation", especially in nontechnical usage.
Fidelity (or "faithfulness") and transparency are two qualities that, for millennia, have been regarded as ideals to be striven for in translation, particularly literary translation. These two ideals are often at odds. Thus a 17th-century French critic coined the phrase, "les belles infidèles," to suggest that translations, like women, could be either faithful or beautiful, but not both at the same time.
Fidelity pertains to the extent to which a translation accurately renders the meaning of the source text, without adding to or subtracting from it, without intensifying or weakening any part of the meaning, and otherwise without distorting it.
Transparency pertains to the extent to which a translation appears to a native speaker of the target language to have originally been written in that language, and conforms to the language's grammatical, syntactic and idiomatic conventions.
A translation that meets the first criterion is said to be a "faithful translation"; a translation that meets the second criterion, an "idiomatic translation." The two qualities are not necessarily mutually exclusive.
The criteria used to judge the faithfulness of a translation vary according to the subject, the precision of the original contents, the type, function and use of the text, its literary qualities, its social or historical context, and so forth.
The criteria for judging the transparency of a translation would appear more straightforward: an unidiomatic translation "sounds wrong," and in the extreme case of word-for-word translations generated by many machine-translation systems, often results in patent nonsense with only a humorous value (see "round-trip translation").
Nevertheless, in certain contexts a translator may consciously strive to produce a literal translation. Literary translators and translators of religious or historic texts often adhere as closely as possible to the source text. In doing so, they often deliberately stretch the boundaries of the target language to produce an unidiomatic text. Similarly, a literary translator may wish to adopt words or expressions from the source language in order to provide "local color" in the translation.
In recent decades, prominent advocates of such "non-transparent" translation have included the French scholar Antoine Berman, who identified twelve deforming tendencies inherent in most prose translations, and the American theorist Lawrence Venuti, who has called upon translators to apply "foreignizing" translation strategies instead of domesticating ones. Many non-transparent-translation theories draw on concepts from German Romanticism, the most obvious influence on latter-day theories of "foreignization" being the German theologian and philosopher Friedrich Schleiermacher. In his seminal lecture "On the Different Methods of Translation" (1813) he distinguished between translation methods that move "the writer toward [the reader]," i.e., transparency, and those that move the "reader toward [the author]," i.e., an extreme fidelity to the foreignness of the source text. Schleiermacher clearly favored the latter approach. His preference was motivated, however, not so much by a desire to embrace the foreign, as by a nationalist desire to oppose France's cultural domination and to promote German literature.
For the most part, current Western practices in translation are dominated by the concepts of "fidelity" and "transparency." This has not always been the case. There have been periods, especially in pre-Classical Rome and in the 18th century, when many translators stepped beyond the bounds of translation proper into the realm of adaptation.
Adapted translation retains currency in some non-Western traditions. Thus the Indian epic, the Ramayana, appears in many versions in the various Indian languages, and the stories are different in each. If one considers the words used for translating into the Indian languages, whether those be Aryan or Dravidian languages, he is struck by the freedom that is granted to the translators. This may relate to a devotion to prophetic passages that strike a deep religious chord, or to a vocation to instruct unbelievers. Similar examples are to be found in medieval Christian literature, which adjusted the text to the customs and values of the audience.
See main article: Dynamic and formal equivalence. The question of fidelity vs. transparency has also been formulated in terms of, respectively, "formal equivalence" and "dynamic equivalence." The latter two expressions are associated with the translator Eugene Nida and were originally coined to describe ways of translating the Bible, but the two approaches are applicable to any translation.
"Formal equivalence" corresponds to "metaphrase," and "dynamic equivalence", to "paraphrase."
"Dynamic equivalence" (or "functional equivalence") conveys the essential thought expressed in a source text — if necessary, at the expense of literality, original sememe and word order, the source text's active vs. passive voice, etc.
By contrast, "formal equivalence" (sought via "literal" translation) attempts to render the text "literally," or "word for word" (the latter expression being itself a word-for-word rendering of the classical Latin "verbum pro verbo") — if necessary, at the expense of features natural to the target language.
There is, however, no sharp boundary between dynamic and formal equivalence. On the contrary, they represent a spectrum of translation approaches. Each is used at various times and in various contexts by the same translator, and at various points within the same text — sometimes simultaneously. Competent translation entails the judicious blending of dynamic and formal equivalents.
A back-translation is a translation of a translated text back into the language of the original text, made without reference to the original text. In the context of machine translation, this is also called a "round-trip translation." It is analogous to reversing a mathematical operation; but even in mathematics such a reversal frequently does not produce a value that is precisely identical with the original.
Comparison of a back-translation to the original text is sometimes used as a quality check on the original translation. But while useful as an approximate check, it is far from infallible. Humorously telling evidence for this was provided by Mark Twain when he issued his own back-translation of a French version of his famous short story, "The Celebrated Jumping Frog of Calaveras County."
In cases when a historic document survives only in translation, the original having been lost, researchers sometimes undertake back-translation in an effort to reconstruct the original text. An example involves the novel The Saragossa Manuscript by the Polish aristocrat Jan Potocki (1761–1815). The polymath polyglot composed the book entirely in French and published fragments anonymously in 1804 and 1813–14. Portions of the original French-language manuscripts were subsequently lost; the missing fragments survived, however, in a Polish translation that was made by Edmund Chojecki in 1847 from a complete French copy, now lost. French-language versions of the complete Saragossa Manuscript have since been produced, based on extant French-language fragments and on French-language versions that have been back-translated from Chojecki's Polish version.
Similarly, when historians suspect that a document is actually a translation from another language, back-translation into that hypothetical original language can provide supporting evidence by showing that such characteristics as idioms, puns, peculiar grammatical structures, etc., are in fact derived from the original language.
For example, the known text of the Till Eulenspiegel folk tales is in High German but contains many puns which only work if back-translated into Low German. This seems clear evidence that these tales (or at least large portions of them) were originally composed in Low German and rendered into High German by an over-metaphrastic translator.
Similarly, supporters of Aramaic primacy—i.e., of the view that the Christian New Testament or its sources were originally written in the Aramaic language—seek to prove their case by showing that difficult passages in the existing Greek text of the New Testament make much better sense if back-translated into Aramaic—that, for example, some incomprehensible references are in fact Aramaic puns which do not work in Greek.
Translation of literary works (novels, short stories, plays, poems, etc.) is considered a literary pursuit in its own right. Notable in Canadian literature specifically as translators are figures such as Sheila Fischman, Robert Dickson and Linda Gaboriau, and the Governor General's Awards annually present prizes for the best English-to-French and French-to-English literary translations.
Other writers, among many who have made a name for themselves as literary translators, include Vasily Zhukovsky, Tadeusz Boy-Żeleński, Vladimir Nabokov, Jorge Luis Borges, Robert Stiller and Haruki Murakami.
The first important translation in the West was that of the Septuagint, a collection of Jewish Scriptures translated into Koine Greek in Alexandria between the 3rd and 1st centuries BCE. The dispersed Jews had forgotten their ancestral language and needed Greek versions (translations) of their Scriptures.
Throughout the Middle Ages, Latin was the lingua franca of the western learned world. The 9th-century Alfred the Great, king of Wessex in England, was far ahead of his time in commissioning vernacular Anglo-Saxon translations of Bede's Ecclesiastical History and Boethius' Consolation of Philosophy. Meanwhile the Christian Church frowned on even partial adaptations of the standard Latin Bible, St. Jerome's Vulgate of ca. 384 CE.
In Asia, the spread of Buddhism led to large-scale ongoing translation efforts spanning well over a thousand years. The Tangut Empire was especially efficient in such efforts; exploiting the then newly-invented block printing, and with the full support of the government (contemporary sources describe the Emperor and his mother personally contributing to the translation effort, alongside sages of various nationalities), the Tanguts took mere decades to translate volumes that had taken the Chinese centuries to render.
Large-scale efforts at translation were undertaken by the Arabs. Having conquered the Greek world, they made Arabic versions of its philosophical and scientific works. During the Middle Ages, some translations of these Arabic versions were made into Latin, chiefly at Córdoba in Spain. Such Latin translations of Greek and original Arab works of scholarship and science would help advance the development of European Scholasticism.
The broad historic trends in Western translation practice may be illustrated on the example of translation into the English language.
The first fine translations into English were made by England's first great poet, the 14th-century Geoffrey Chaucer, who adapted from the Italian of Giovanni Boccaccio in his own Knight's Tale and Troilus and Criseyde; began a translation of the French-language Roman de la Rose; and completed a translation of Boethius from the Latin. Chaucer founded an English poetic tradition on adaptations and translations from those earlier-established literary languages.
The first great English translation was the Wycliffe Bible (ca. 1382), which showed the weaknesses of an underdeveloped English prose. Only at the end of the 15th century would the great age of English prose translation begin with Thomas Malory's Le Morte Darthur—an adaptation of Arthurian romances so free that it can, in fact, hardly be called a true translation. The first great Tudor translations are, accordingly, the Tyndale New Testament (1525), which would influence the Authorized Version (1611), and Lord Berners' version of Jean Froissart's Chronicles (1523–25).
Meanwhile, in Renaissance Italy, a new period in the history of translation had opened in Florence with the arrival, at the court of Cosimo de' Medici, of the Byzantine scholar Georgius Gemistus Pletho shortly before the fall of Constantinople to the Turks (1453). A Latin translation of Plato's works was undertaken by Marsilio Ficino. This and Erasmus' Latin edition of the New Testament led to a new attitude to translation. For the first time, readers demanded rigor of rendering, as philosophical and religious beliefs depended on the exact words of Plato, Aristotle and Jesus.
Non-scholarly literature, however, continued to rely on adaptation. France's Pléiade, England's Tudor poets, and the Elizabethan translators adapted themes by Horace, Ovid, Petrarch and modern Latin writers, forming a new poetic style on those models. The English poets and translators sought to supply a new public, created by the rise of a middle class and the development of printing, with works such as the original authors would have written, had they been writing in England in that day.
The Elizabethan period of translation saw considerable progress beyond mere paraphrase toward an ideal of stylistic equivalence, but even to the end of this period—which actually reached to the middle of the 17th century—there was no concern for verbal accuracy.
In the second half of the 17th century, the poet John Dryden sought to make Virgil speak "in words such as he would probably have written if he were living and an Englishman." Dryden, however, discerned no need to emulate the Roman poet's subtlety and concision. Similarly, Homer suffered from Alexander Pope's endeavor to reduce the Greek poet's "wild paradise" to order.
Throughout the 18th century, the watchword of translators was ease of reading. Whatever they did not understand in a text, or thought might bore readers, they omitted. They cheerfully assumed that their own style of expression was the best, and that texts should be made to conform to it in translation. For scholarship they cared no more than had their predecessors, and they did not shrink from making translations from translations in third languages, or from languages that they hardly knew, or—as in the case of James Macpherson's "translations" of Ossian—from texts that were actually of the "translator's" own composition.
The 19th century brought new standards of accuracy and style. In regard to accuracy, observes J.M. Cohen, the policy became "the text, the whole text, and nothing but the text," except for any bawdy passages and the addition of copious explanatory footnotes. In regard to style, the Victorians' aim, achieved through far-reaching metaphrase (literality) or pseudo-metaphrase, was to constantly remind readers that they were reading a foreign classic. An exception was the outstanding translation in this period, Edward FitzGerald's Rubaiyat of Omar Khayyam (1859), which achieved its Oriental flavor largely by using Persian names and discreet Biblical echoes and actually drew little of its material from the Persian original.
In advance of the 20th century, a new pattern was set in 1871 by Benjamin Jowett, who translated Plato into simple, straightforward language. Jowett's example was not followed, however, until well into the new century, when accuracy rather than style became the principal criterion.
Poetry presents special challenges to translators, given the importance of a text's formal aspects, in addition to its content. In his influential 1959 paper "On Linguistic Aspects of Translation," the Russian-born linguist and semiotician Roman Jakobson went so far as to declare that "poetry by definition [is] untranslatable."
In 1974 the American poet James Merrill wrote a poem, "Lost in Translation," which in part explores this idea. The question was also discussed in Douglas Hofstadter's 1997 book, Le Ton beau de Marot; he argues that a good translation of a poem must convey as much as possible not only of its literal meaning, but of its form and structure (meter, rhyme or alliteration scheme, etc.).
Translation of a text that is sung in vocal music for the purpose of singing in another language — sometimes called "singing translation" — is closely linked to translation of poetry because most vocal music, at least in the Western tradition, is set to verse, especially verse in regular patterns with rhyme. (Since the late 19th century, musical setting of prose and free verse has also been practiced in some art music, though popular music tends to remain conservative in its retention of stanzaic forms with or without refrains.) A rudimentary example of translating poetry for singing is church hymns, such as the German chorales translated into English by Catherine Winkworth. 
Translation of sung texts is generally much more restrictive than translation of poetry, because in the former there is little or no freedom to choose between a versified translation and a translation that dispenses with verse structure. One might modify or omit rhyme in a singing translation, but the assignment of syllables to specific notes in the original musical setting places great challenges on the translator. There is the option in prose sung texts, less so in verse, of adding or deleting a syllable here and there by subdividing or combining notes, respectively, but even with prose the process is almost like strict verse translation because of the need to stick as closely as possible to the original prosody of the sung melodic line.
Other considerations in writing a singing translation include repetition of words and phrases, the placement of rests and/or punctuation, the quality of vowels sung on high notes, and rhythmic features of the vocal line that may be more natural to the original language than to the target language. A sung translation may be considerably or completely different from the original, thus resulting in a contrafactum.
Translations of sung texts — whether of the above type meant to be sung or of a more or less literal type meant to be read — are also used as aids to audiences, singers and conductors, when a work is being sung in a language not known to them. The most familiar types are translations presented as subtitles projected during opera performances, those inserted into concert programs, and those that accompany commercial audio CDs of vocal music. In addition, professional and amateur singers often sing works in languages they do not know (or do not know well), and translations are then used to enable them to understand the meaning of the words they are singing.
Discussions of the theory and practice of translation reach back into antiquity and show remarkable continuities. The distinction that had been drawn by the ancient Greeks between "metaphrase" ("literal" translation) and "paraphrase" would be adopted by the English poet and translator John Dryden (1631-1700), who represented translation as the judicious blending of these two modes of phrasing when selecting, in the target language, "counterparts," or equivalents, for the expressions used in the source language:
Dryden cautioned, however, against the license of "imitation," i.e. of adapted translation: "When a painter copies from the life... he has no privilege to alter features and lineaments..." This general formulation of the central concept of translation — equivalence — is probably as adequate as any that has been proposed ever since Cicero and Horace, in first-century-BCE Rome, famously and literally cautioned against translating "word for word" ("verbum pro verbo").
Despite occasional theoretical diversities, the actual practice of translators has hardly changed since antiquity. Except for some extreme metaphrasers in the early Christian period and the Middle Ages, and adapters in various periods (especially pre-Classical Rome, and the 18th century), translators have generally shown prudent flexibility in seeking equivalents — "literal" where possible, paraphrastic where necessary — for the original meaning and other crucial "values" (e.g., style, verse form, concordance with musical accompaniment or, in films, with speech articulatory movements) as determined from context.
In general, translators have sought to preserve the context itself by reproducing the original order of sememes, and hence word order — when necessary, reinterpreting the actual grammatical structure. The grammatical differences between "fixed-word-order" languages (e.g., English, French, German) and "free-word-order" languages (e.g., Greek, Latin, Polish, Russian) have been no impediment in this regard.
When a target language has lacked terms that are found in a source language, translators have borrowed them, thereby enriching the target language. Thanks in great measure to the exchange of calques and loanwords between languages, and to their importation from other languages, there are few concepts that are "untranslatable" among the modern European languages. In general, the greater the contact and exchange that has existed between two languages, or between both and a third one, the greater is the ratio of metaphrase to paraphrase that may be used in translating between them. However, due to shifts in "ecological niches" of words, a common etymology is sometimes misleading as a guide to current meaning in one or the other language. The English "actual," for example, should not be confused with the cognate French "actuel" (meaning "present," "current") or the Polish "aktualny" ("present," "current").
The translator's role as a bridge for "carrying across" values between cultures has been discussed at least since Terence, Roman adapter of Greek comedies, in the second century BCE. The translator's role is, however, by no means a passive and mechanical one, and so has also been compared to that of an artist. The main ground seems to be the concept of parallel creation found in critics as early as Cicero. Dryden observed that "Translation is a type of drawing after life..." Comparison of the translator with a musician or actor goes back at least to Samuel Johnson's remark about Alexander Pope playing Homer on a flageolet, while Homer himself used a bassoon. If translation be an art, it is no easy one. In the 13th century, Roger Bacon wrote that if a translation is to be true, the translator must know both languages, as well as the science that he is to translate; and finding that few translators did, he wanted to do away with translation and translators altogether. The first European to assume that one translates satisfactorily only toward his own language may have been Martin Luther, translator of the Bible into German. According to L.G. Kelly, since Johann Gottfried Herder in the 18th century, "it has been axiomatic" that one works only toward his own language.
Compounding these demands upon the translator is the fact that not even the most complete dictionary or thesaurus can ever be a fully adequate guide in translation. Alexander Tytler, in his Essay on the Principles of Translation (1790), emphasized that assiduous reading is a more comprehensive guide to a language than are dictionaries. The same point, but also including listening to the spoken language, had earlier been made in 1783 by Onufry Andrzej Kopczyński, member of Poland's Society for Elementary Books, who was called "the last Latin poet." The special role of the translator in society was well described in an essay, published posthumously in 1803, by Ignacy Krasicki — "Poland's La Fontaine", Primate of Poland, poet, encyclopedist, author of the first Polish novel, and translator from French and Greek:
Translation of religious works has played an important role in history. Buddhist monks who translated the Indian sutras into Chinese often skewed their translations to better reflect China's very different culture, emphasizing notions such as filial piety.
A famous mistranslation of the Bible is the rendering of the Hebrew word "keren," which has several meanings, as "horn" in a context where it actually means "beam of light." As a result, artists have for centuries depicted Moses the Lawgiver with horns growing out of his forehead. An example is Michelangelo's famous sculpture. Some Christians with anti-Semitic feelings used such depictions to spread hatred of the Jews, claiming that they were devils with horns.
One of the first recorded instances of translation in the West was the rendering of the Old Testament into Greek in the third century B.C.E. The resulting translation is known as the Septuagint, a name that alludes to the "seventy" translators (seventy-two in some versions) who were commissioned to translate the Bible in Alexandria. Each translator worked in solitary confinement in a separate cell, and legend has it that all seventy versions were identical. The Septuagint became the source text for later translations into many languages, including Latin, Coptic, Armenian and Georgian.
Saint Jerome, the patron saint of translation, is still considered one of the greatest translators in history for rendering the Bible into Latin. The Roman Catholic Church used his translation (known as the Vulgate) for centuries, but even this translation at first stirred much controversy.
The period preceding and contemporary with the Protestant Reformation saw the translation of the Bible into local European languages, a development that greatly affected Western Christianity's split into Roman Catholicism and Protestantism, due to disparities between Catholic and Protestant versions of crucial words and passages.
See main article: Machine translation. Machine translation (MT) is a procedure whereby a computer program analyzes a source text and produces a target text without further human intervention. In reality, however, machine translation typically does involve human intervention, in the form of pre-editing and post-editing. An exception to that rule might be, e.g., the translation of technical specifications (strings of technical terms and adjectives), using a dictionary-based machine-translation system.
To date, machine translation—a major goal of natural-language processing—has met with limited success. A November 6, 2007, example illustrates the hazards of uncritical reliance on machine translation.
Machine translation has been brought to a large public by tools available on the Internet, such as Yahoo!'s Babel Fish, Babylon, and StarDict. These tools produce a "gisting translation" — a rough translation that, with luck, "gives the gist" of the source text.
With proper terminology work, with preparation of the source text for machine translation (pre-editing), and with re-working of the machine translation by a professional human translator (post-editing), commercial machine-translation tools can produce useful results, especially if the machine-translation system is integrated with a translation-memory or globalization-management system. 
In regard to texts (e.g., weather reports) with limited ranges of vocabulary and simple sentence structure, machine translation can deliver results that do not require much human intervention to be useful. Also, the use of a controlled language, combined with a machine-translation tool, will typically generate largely comprehensible translations.
Relying exclusively on unedited machine translation ignores the fact that communication in human language is context-embedded and that it takes a person to comprehend the context of the original text with a reasonable degree of probability. It is certainly true that even purely human-generated translations are prone to error. Therefore, to ensure that a machine-generated translation will be useful to a human being and that publishable-quality translation is achieved, such translations must be reviewed and edited by a human. The late Claude Piron wrote that machine translation, at its best, automates the easier part of a translator's job; the harder and more time-consuming part usually involves doing extensive research to resolve ambiguities in the source text, which the grammatical and lexical exigencies of the target language require to be resolved. Such research is a necessary prelude to the pre-editing necessary in order to provide input for machine-translation software such that the output will not be meaningless.
See main article: Computer-assisted translation. Computer-assisted translation (CAT), also called "computer-aided translation," "machine-aided human translation (MAHT)" and "interactive translation," is a form of translation wherein a human translator creates a target text with the assistance of a computer program. The machine supports a human translator.
Computer-assisted translation can include standard dictionary and grammar software. The term, however, normally refers to a range of specialized programs available to the translator, including translation-memory, terminology-management, concordance, and alignment programs.
With the internet, translation software can help non-native-speaking individuals understand web pages published in other languages. Whole-page translation tools are of limited utility, however, since they offer only a limited potential understanding of the original author's intent and context; translated pages tend to be more humorous and confusing than enlightening.
Interactive translations with pop-up windows are becoming more popular. These tools show several possible translations of each word or phrase. Human operators merely need to select the correct translation as the mouse glides over the foreign-language text. Possible definitions can be grouped by pronunciation.