TedTest

From the Ted Talk by Ioannis Papachimonas: How computers translate human language

Unscramble the Blue Letters

How is it that so many intergalactic speiecs in movies and TV just hpaepn to saepk perfect English? The short answer is that no one wants to watch a starship crew senpd years compiling an alien dictionary. But to keep things consistent, the creators of Star Trek and other science-fiction wolrds have introduced the concept of a urviaesnl translator, a portable device that can instantly translate between any languages. So is a universal translator possible in real life? We already have many programs that claim to do just that, taking a word, sentence, or entire book in one language and tninasalrtg it into almost any other, whether it's modern English or Ancient Sanskrit. And if tarnlatison were just a matter of looking up words in a dictionary, these poarmgrs would run circles around hamnus. The reality, however, is a bit more complicated. A rule-based translation program uses a lexical database, which includes all the wrods you'd find in a dictionary and all grammatical forms they can take, and set of rules to rziogcene the basic linguistic elements in the input language. For a seemingly simple sentence like, "The children eat the mfiufns," the program first psaers its snyatx, or grammatical structure, by ideiityfnng the children as the subject, and the rest of the sentence as the predicate consisting of a verb "eat," and a direct object "the muffins." It then needs to recognize English morphology, or how the lguaange can be broken down into its smallest meaningful uitns, such as the word muffin and the suffix "s," used to indicate plural. Finally, it needs to understand the semantics, what the different parts of the sentence actually mean. To translate this sentence properly, the program would refer to a different set of vaborcaluy and rules for each element of the target language. But this is where it gets tricky. The syntax of some languages allows words to be arranged in any order, while in others, doing so could make the muffin eat the child. Morphology can also pose a problem. Slovene dsgthuisniies between two children and three or more using a dual suiffx absent in many other languages, while Russian's lack of dinfetie aeirtcls might leave you wondering whether the children are eating some particular muffins, or just eat muffins in general. Finally, even when the semantics are technically correct, the program might miss their finer points, such as whether the cldirhen "mangiano" the muffins, or "divorano" them. Another method is statistical machine translation, which alyzaens a database of books, articles, and documents that have already been translated by humans. By finding matches between source and translated text that are unlikely to occur by cahnce, the program can idtneify corresponding phrases and patterns, and use them for future translations. However, the quality of this type of translation depends on the size of the initial database and the availability of samples for certain languages or slteys of writing. The difficulty that computers have with the exceptions, ilgeirrrietuas and shdeas of meaning that seem to come instinctively to humans has led some researchers to believe that our understanding of language is a unique pcorudt of our biological brain srrttcuue. In fact, one of the most famous fictional universal translators, the Babel fish from "The Hitchhiker's Guide to the Galaxy", is not a machine at all but a small craturee that tnelsatras the brain waves and nerve signals of sentient species through a form of telepathy. For now, learning a language the old fashioned way will still give you better results than any currently available computer program. But this is no easy task, and the sheer number of languages in the world, as well as the increasing interaction between the pelpoe who speak them, will only continue to spur greater advances in autaimotc translation. Perhaps by the time we encounter intergalactic life forms, we'll be able to concuatmmie with them through a tiny gimzo, or we might have to start compiling that dictionary, after all.

Open Cloze

How is it that so many intergalactic _______ in movies and TV just ______ to _____ perfect English? The short answer is that no one wants to watch a starship crew _____ years compiling an alien dictionary. But to keep things consistent, the creators of Star Trek and other science-fiction ______ have introduced the concept of a _________ translator, a portable device that can instantly translate between any languages. So is a universal translator possible in real life? We already have many programs that claim to do just that, taking a word, sentence, or entire book in one language and ___________ it into almost any other, whether it's modern English or Ancient Sanskrit. And if ___________ were just a matter of looking up words in a dictionary, these ________ would run circles around ______. The reality, however, is a bit more complicated. A rule-based translation program uses a lexical database, which includes all the _____ you'd find in a dictionary and all grammatical forms they can take, and set of rules to _________ the basic linguistic elements in the input language. For a seemingly simple sentence like, "The children eat the _______," the program first ______ its ______, or grammatical structure, by ___________ the children as the subject, and the rest of the sentence as the predicate consisting of a verb "eat," and a direct object "the muffins." It then needs to recognize English morphology, or how the ________ can be broken down into its smallest meaningful _____, such as the word muffin and the suffix "s," used to indicate plural. Finally, it needs to understand the semantics, what the different parts of the sentence actually mean. To translate this sentence properly, the program would refer to a different set of __________ and rules for each element of the target language. But this is where it gets tricky. The syntax of some languages allows words to be arranged in any order, while in others, doing so could make the muffin eat the child. Morphology can also pose a problem. Slovene _____________ between two children and three or more using a dual ______ absent in many other languages, while Russian's lack of ________ ________ might leave you wondering whether the children are eating some particular muffins, or just eat muffins in general. Finally, even when the semantics are technically correct, the program might miss their finer points, such as whether the ________ "mangiano" the muffins, or "divorano" them. Another method is statistical machine translation, which ________ a database of books, articles, and documents that have already been translated by humans. By finding matches between source and translated text that are unlikely to occur by ______, the program can ________ corresponding phrases and patterns, and use them for future translations. However, the quality of this type of translation depends on the size of the initial database and the availability of samples for certain languages or ______ of writing. The difficulty that computers have with the exceptions, ______________ and ______ of meaning that seem to come instinctively to humans has led some researchers to believe that our understanding of language is a unique _______ of our biological brain _________. In fact, one of the most famous fictional universal translators, the Babel fish from "The Hitchhiker's Guide to the Galaxy", is not a machine at all but a small ________ that __________ the brain waves and nerve signals of sentient species through a form of telepathy. For now, learning a language the old fashioned way will still give you better results than any currently available computer program. But this is no easy task, and the sheer number of languages in the world, as well as the increasing interaction between the ______ who speak them, will only continue to spur greater advances in _________ translation. Perhaps by the time we encounter intergalactic life forms, we'll be able to ___________ with them through a tiny _____, or we might have to start compiling that dictionary, after all.

Solution

irregularities
humans
species
translates
structure
translating
language
identifying
worlds
programs
happen
articles
recognize
shades
people
universal
units
definite
communicate
syntax
automatic
identify
vocabulary
distinguishes
speak
spend
gizmo
analyzes
suffix
creature
children
chance
styles
product
words
parses
translation
muffins

Original Text

How is it that so many intergalactic species in movies and TV just happen to speak perfect English? The short answer is that no one wants to watch a starship crew spend years compiling an alien dictionary. But to keep things consistent, the creators of Star Trek and other science-fiction worlds have introduced the concept of a universal translator, a portable device that can instantly translate between any languages. So is a universal translator possible in real life? We already have many programs that claim to do just that, taking a word, sentence, or entire book in one language and translating it into almost any other, whether it's modern English or Ancient Sanskrit. And if translation were just a matter of looking up words in a dictionary, these programs would run circles around humans. The reality, however, is a bit more complicated. A rule-based translation program uses a lexical database, which includes all the words you'd find in a dictionary and all grammatical forms they can take, and set of rules to recognize the basic linguistic elements in the input language. For a seemingly simple sentence like, "The children eat the muffins," the program first parses its syntax, or grammatical structure, by identifying the children as the subject, and the rest of the sentence as the predicate consisting of a verb "eat," and a direct object "the muffins." It then needs to recognize English morphology, or how the language can be broken down into its smallest meaningful units, such as the word muffin and the suffix "s," used to indicate plural. Finally, it needs to understand the semantics, what the different parts of the sentence actually mean. To translate this sentence properly, the program would refer to a different set of vocabulary and rules for each element of the target language. But this is where it gets tricky. The syntax of some languages allows words to be arranged in any order, while in others, doing so could make the muffin eat the child. Morphology can also pose a problem. Slovene distinguishes between two children and three or more using a dual suffix absent in many other languages, while Russian's lack of definite articles might leave you wondering whether the children are eating some particular muffins, or just eat muffins in general. Finally, even when the semantics are technically correct, the program might miss their finer points, such as whether the children "mangiano" the muffins, or "divorano" them. Another method is statistical machine translation, which analyzes a database of books, articles, and documents that have already been translated by humans. By finding matches between source and translated text that are unlikely to occur by chance, the program can identify corresponding phrases and patterns, and use them for future translations. However, the quality of this type of translation depends on the size of the initial database and the availability of samples for certain languages or styles of writing. The difficulty that computers have with the exceptions, irregularities and shades of meaning that seem to come instinctively to humans has led some researchers to believe that our understanding of language is a unique product of our biological brain structure. In fact, one of the most famous fictional universal translators, the Babel fish from "The Hitchhiker's Guide to the Galaxy", is not a machine at all but a small creature that translates the brain waves and nerve signals of sentient species through a form of telepathy. For now, learning a language the old fashioned way will still give you better results than any currently available computer program. But this is no easy task, and the sheer number of languages in the world, as well as the increasing interaction between the people who speak them, will only continue to spur greater advances in automatic translation. Perhaps by the time we encounter intergalactic life forms, we'll be able to communicate with them through a tiny gizmo, or we might have to start compiling that dictionary, after all.

Frequently Occurring Word Combinations

Important Words

absent
advances
alien
analyzes
ancient
answer
arranged
articles
automatic
availability
babel
basic
biological
bit
book
books
brain
broken
chance
child
children
circles
claim
communicate
compiling
complicated
computer
computers
concept
consistent
consisting
continue
correct
creators
creature
crew
database
definite
depends
device
dictionary
difficulty
direct
distinguishes
documents
dual
easy
eat
eating
element
elements
encounter
english
entire
exceptions
fact
famous
fashioned
fictional
finally
find
finding
finer
fish
form
forms
future
general
give
gizmo
grammatical
greater
guide
happen
humans
identify
identifying
includes
increasing
initial
input
instantly
instinctively
interaction
intergalactic
introduced
irregularities
lack
language
languages
learning
leave
led
lexical
life
linguistic
machine
matches
matter
meaning
meaningful
method
modern
morphology
movies
muffin
muffins
nerve
number
object
occur
order
parses
parts
patterns
people
perfect
phrases
plural
points
portable
pose
predicate
problem
product
program
programs
properly
quality
real
reality
recognize
refer
researchers
rest
results
rules
run
samples
sanskrit
seemingly
semantics
sentence
sentient
set
shades
sheer
short
signals
simple
size
slovene
small
smallest
source
speak
species
spend
spur
star
starship
start
statistical
structure
styles
subject
suffix
syntax
target
task
technically
telepathy
text
time
tiny
translate
translated
translates
translating
translation
translations
translator
translators
trek
tricky
tv
type
understand
understanding
unique
units
universal
verb
vocabulary
watch
waves
wondering
word
words
world
worlds
writing
years