Latest inventions in natural language tools


Natural language processing

Natural language processing (NLP) is a
subfield of artificial intelligence andDo  the  girls  look  little?
linguistics. It studies the problems of
automated generation and understanding ofDo  the  girls  look  pretty?
natural human languages. Natural language
generation systems convert information fromDoes  the  school  look  pretty?
computer databases into normal-sounding human
language, and natural language understandingSubproblems
systems convert samples of human language
into more formal representations that areSpeech  segmentation
easier  for  computer programs to manipulate.
In most spoken languages, the sounds
Tasks  and  limitationsrepresenting successive letters blend into
each other, so the conversion of the analog
In theory natural language processing is asignal to discrete characters can be a very
very attractive method of human-computerdifficult process. Also, in natural speech
interaction. Early systems such as SHRDLU,there are hardly any pauses between
working in restricted "blocks worlds" withsuccessive words; the location of those
restricted vocabularies, worked extremelyboundaries usually must take into account
well, leading researchers to excessivegrammatical and semantical constraints, as
optimism which was soon lost when the systemswell  as  the  context.
were extended to more realistic situations
with  real-world  ambiguity  and  complexity.Text  segmentation
Natural language understanding is sometimesSome written languages like Chinese,
referred to as an AI-complete problem,Japanese and Thai do not have single word
because natural language recognition seems toboundaries either, so any significant text
require extensive knowledge about the outsideparsing usually requires the identification
world and the ability to manipulate it. Theof word boundaries, which is often a
definition of "understanding" is one of thenon-trivial  task.
major problems in natural language
processing.Word  sense  disambiguation
Concrete  problemsMany words have more than one meaning; we
have to select the meaning which makes the
Some examples of the problems faced bymost  sense  in  context.
natural  language  understanding  systems:
Syntactic  ambiguity
The sentences We gave the monkeys the bananas
because they were hungry and We gave theThe grammar for natural languages is
monkeys the bananas because they wereambiguous, i.e. there are often multiple
over-ripe have the same surface grammaticalpossible parse trees for a given sentence.
structure. However, in one of them the wordChoosing the most appropriate one usually
they refers to the monkeys, in the other itrequires semantic and contextual information.
refers to the bananas: the sentence cannot beSpecific problem components of syntactic
understood properly without knowledge of theambiguity include sentence boundary
properties and behaviour of monkeys anddisambiguation.
bananas.
Imperfect  or  irregular  input
A string of words may be interpreted in
myriad ways. For example, the string TimeForeign or regional accents and vocal
flies like an arrow may be interpreted in aimpediments in speech; typing or grammatical
variety  of  ways:errors,  OCR  errors  in  texts.
time  moves  quickly just like an arrow does;Speech  acts  and  plans
measure the speed of flying insects like youSentences often don't mean what they
would measure that of an arrow - i.e. (Youliterally say; for instance a good answer to
should)  time flies like you would an arrow.;"Can you pass the salt" is to pass the salt;
in most contexts "Yes" is not a good answer,
measure the speed of flying insects like analthough "No" is better and "I'm afraid that
arrow would - i.e. Time flies in the same wayI can't see it" is better yet. Or again, if a
that  an  arrow  would  (time  them).;class was not offered last year, "The class
was not offered last year" is a better answer
measure the speed of flying insects that areto the question "How many students failed the
like arrows - i.e. Time those flies that areclass  last  year?"  than  "None"  is.
like  arrows;
Statistical  NLP
a type of flying insect, "time-flies," enjoy
arrows  (compare  Fruit flies like a banana.)Statistical natural language processing uses
stochastic, probabilistic and statistical
English is particularly challenging in thismethods to resolve some of the difficulties
regard because it has little inflectionaldiscussed above, especially those which arise
morphology to distinguish between parts ofbecause longer sentences are highly ambiguous
speech.when processed with realistic grammars,
yielding thousands or millions of possible
English and several other languages don'tanalyses. Methods for disambiguation often
specify which word an adjective applies to.involve the use of corpora and Markov models.
For example, in the string "pretty littleThe technology for statistical NLP comes
girls'  school".mainly from machine learning and data mining,
both of which are fields of artificial
Does  the  school  look  little?intelligence that involve learning from data.



1 A B C D 58 59 60 61 62 63 64 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108