1
00:00:06,677 --> 00:00:11,306
How is it that so many 
intergalactic species in movies and TV

2
00:00:11,306 --> 00:00:14,483
just happen to speak perfect English?

3
00:00:14,483 --> 00:00:17,886
The short answer is that no one
wants to watch a starship crew

4
00:00:17,886 --> 00:00:21,774
spend years compiling an alien dictionary.

5
00:00:21,774 --> 00:00:23,392
But to keep things consistent,

6
00:00:23,392 --> 00:00:26,789
the creators of Star Trek
and other science-fiction worlds

7
00:00:26,789 --> 00:00:30,514
have introduced the concept
of a universal translator,

8
00:00:30,514 --> 00:00:35,012
a portable device that can instantly
translate between any languages.

9
00:00:35,012 --> 00:00:38,539
So is a universal translator 
possible in real life?

10
00:00:38,539 --> 00:00:42,137
We already have many programs
that claim to do just that,

11
00:00:42,137 --> 00:00:45,954
taking a word, sentence, 
or entire book in one language

12
00:00:45,954 --> 00:00:49,004
and translating it into almost any other,

13
00:00:49,004 --> 00:00:52,337
whether it's modern English
or Ancient Sanskrit.

14
00:00:52,337 --> 00:00:55,913
And if translation were just a matter
of looking up words in a dictionary,

15
00:00:55,913 --> 00:00:59,825
these programs would run circles
around humans.

16
00:00:59,825 --> 00:01:03,299
The reality, however, 
is a bit more complicated.

17
00:01:03,299 --> 00:01:07,349
A rule-based translation program
uses a lexical database,

18
00:01:07,349 --> 00:01:10,302
which includes all the words 
you'd find in a dictionary

19
00:01:10,302 --> 00:01:13,283
and all grammatical forms they can take,

20
00:01:13,283 --> 00:01:18,925
and set of rules to recognize the basic
linguistic elements in the input language.

21
00:01:18,925 --> 00:01:22,396
For a seemingly simple sentence like,
"The children eat the muffins,"

22
00:01:22,396 --> 00:01:27,050
the program first parses its syntax,
or grammatical structure,

23
00:01:27,050 --> 00:01:29,587
by identifying the children 
as the subject,

24
00:01:29,587 --> 00:01:32,317
and the rest of the sentence 
as the predicate

25
00:01:32,317 --> 00:01:34,368
consisting of a verb "eat,"

26
00:01:34,368 --> 00:01:37,422
and a direct object "the muffins."

27
00:01:37,422 --> 00:01:40,249
It then needs to recognize
English morphology,

28
00:01:40,249 --> 00:01:44,681
or how the language can be broken down
into its smallest meaningful units,

29
00:01:44,681 --> 00:01:46,124
such as the word muffin

30
00:01:46,124 --> 00:01:49,755
and the suffix "s," 
used to indicate plural.

31
00:01:49,755 --> 00:01:52,449
Finally, it needs to understand 
the semantics,

32
00:01:52,449 --> 00:01:56,178
what the different parts of the sentence
actually mean.

33
00:01:56,178 --> 00:01:58,074
To translate this sentence properly,

34
00:01:58,074 --> 00:02:01,982
the program would refer to a different set
of vocabulary and rules

35
00:02:01,982 --> 00:02:05,166
for each element of the target language.

36
00:02:05,166 --> 00:02:07,020
But this is where it gets tricky.

37
00:02:07,020 --> 00:02:11,820
The syntax of some languages
allows words to be arranged in any order,

38
00:02:11,820 --> 00:02:16,954
while in others, doing so could make
the muffin eat the child.

39
00:02:16,954 --> 00:02:19,647
Morphology can also pose a problem.

40
00:02:19,647 --> 00:02:23,243
Slovene distinguishes between
two children and three or more

41
00:02:23,243 --> 00:02:27,097
using a dual suffix absent 
in many other languages,

42
00:02:27,097 --> 00:02:30,532
while Russian's lack of definite articles
might leave you wondering

43
00:02:30,532 --> 00:02:33,575
whether the children are eating 
some particular muffins,

44
00:02:33,575 --> 00:02:36,719
or just eat muffins in general.

45
00:02:36,719 --> 00:02:39,708
Finally, even when the semantics
are technically correct,

46
00:02:39,708 --> 00:02:42,757
the program might miss their finer points,

47
00:02:42,757 --> 00:02:45,809
such as whether the children 
"mangiano" the muffins,

48
00:02:45,809 --> 00:02:47,794
or "divorano" them.

49
00:02:47,794 --> 00:02:51,558
Another method is 
statistical machine translation,

50
00:02:51,558 --> 00:02:55,762
which analyzes a database 
of books, articles, and documents

51
00:02:55,762 --> 00:02:59,488
that have already 
been translated by humans.

52
00:02:59,488 --> 00:03:02,959
By finding matches between source
and translated text

53
00:03:02,959 --> 00:03:05,393
that are unlikely to occur by chance,

54
00:03:05,393 --> 00:03:09,345
the program can identify corresponding
phrases and patterns,

55
00:03:09,345 --> 00:03:12,429
and use them for future translations.

56
00:03:12,429 --> 00:03:14,969
However, the quality 
of this type of translation

57
00:03:14,969 --> 00:03:17,690
depends on the size 
of the initial database

58
00:03:17,690 --> 00:03:21,357
and the availability of samples 
for certain languages

59
00:03:21,357 --> 00:03:23,383
or styles of writing.

60
00:03:23,383 --> 00:03:27,140
The difficulty that computers have
with the exceptions, irregularities

61
00:03:27,140 --> 00:03:30,994
and shades of meaning
that seem to come instinctively to humans

62
00:03:30,994 --> 00:03:35,045
has led some researchers to believe
that our understanding of language

63
00:03:35,045 --> 00:03:39,251
is a unique product 
of our biological brain structure.

64
00:03:39,251 --> 00:03:43,101
In fact, one of the most famous
fictional universal translators,

65
00:03:43,101 --> 00:03:46,439
the Babel fish from 
"The Hitchhiker's Guide to the Galaxy",

66
00:03:46,439 --> 00:03:49,726
is not a machine at all
but a small creature

67
00:03:49,726 --> 00:03:54,210
that translates the brain waves
and nerve signals of sentient species

68
00:03:54,210 --> 00:03:57,005
through a form of telepathy.

69
00:03:57,005 --> 00:03:59,726
For now, learning a language
the old fashioned way

70
00:03:59,726 --> 00:04:05,106
will still give you better results than
any currently available computer program.

71
00:04:05,106 --> 00:04:06,749
But this is no easy task,

72
00:04:06,749 --> 00:04:09,014
and the sheer number 
of languages in the world,

73
00:04:09,014 --> 00:04:12,989
as well as the increasing interaction
between the people who speak them,

74
00:04:12,989 --> 00:04:18,004
will only continue to spur greater
advances in automatic translation.

75
00:04:18,004 --> 00:04:21,409
Perhaps by the time we encounter
intergalactic life forms,

76
00:04:21,409 --> 00:04:24,660
we'll be able to communicate with them
through a tiny gizmo,

77
00:04:24,660 --> 00:04:29,026
or we might have to start compiling
that dictionary, after all.