Natural Language Processing (NLP) is a subfield of artificial intelligence and linguistics. It studies the problems inherent in the processing and manipulation of natural language, and, natural language understanding devoted to making computers "understand" statements written in human languages.

Natural language processing

Early systems such as SHRDLU, working in restricted "blocks worlds " with restricted vocabularies, worked extremely well, leading researchers to excessive optimism which was soon lost when the systems were extended to more realistic situations with real-world ambiguity and complexity.

Natural language understanding is sometimes referred to as an AI-complete problem, because natural language recognition seems to require extensive knowledge about the outside world and the ability to manipulate it. The definition of "understanding" is one of the major problems in natural language processing.

Some examples of the problems faced by natural language understanding systems:

• The sentences We gave the monkeys the bananas because they were hungry and We gave the monkeys the bananas because they were over-ripe have the same surface grammatical structure. However, in one of them the word they refers to the monkeys, in the other it refers to the bananas: the sentence cannot be understood properly without knowledge of the properties and behaviour of monkeys and bananas.

• A string of words may be interpreted in myriad ways. For example, the string Time flies like an arrow may be interpreted in a variety of ways:
  • time moves quickly just like an arrow does;
  • measure the speed of flying insects like you would measure that of an arrow;
  • measure the speed of flying insects like an arrow would;
  • measure the speed of flying insects that are like arrows;
  • a type of flying insect, "time-flies," enjoy arrows (compare Fruit flies like a banana.)

The word "time" alone can be interpreted as three different parts of speech, (noun in the first example, verb in 2, 3, 4, and adjective in 5).

English is particularly challenging in this regard because it has little inflectional morphology to distinguish between parts of speech.

• English and several other languages don't specify which word an adjective applies to. For example, in the string "pretty little girls' school".
  • Does the school look little?
  • Do the girls look little?
  • Do the girls look pretty?
  • Does the school look pretty?

To help this problem, some linguists and artificial intelligence researchers have proposed using an artificial language, that is capable of expressing all the nuance and subtlety of the natural languages we are familiar with, but would have mathematically inviolate grammar and spelling rules, to remove all possible confusion about what a sentence is trying to say, even if it were nonsense words. An example of such a constructed language that could be used for higher order human/computer communication is lojban.

The major tasks in NLP

• Text to speech
• Speech recognition
• Natural language generation
• Machine translation
• Question answering
• Information retrieval
• Information extraction
• Text-proofing
• Translation technology
• Automatic Summarization (text summaries)

Some problems which make NLP difficult

Word boundary detection  

In spoken language, there are usually no gaps between words; where to place the word boundary often depends on what choice makes the most sense grammatically and given the context. In written form, languages like Chinese do not signal word boundaries either.

Word sense disambiguation 

Many words have more than one meaning; we have to select the meaning which makes the most sense in context.

Syntactic ambiguity 

The grammar for natural languages is not unambiguous , i.e. there are often multiple possible parse trees for a given sentence. Choosing the most appropriate one usually requires semantic and contextual information.

Imperfect or irregular input 

Foreign or regional accents and vocal impediments in speech; typing or grammatical errors, OCR errors in texts.

Speech acts and plans 

Sentences often don't mean what they literally say; for instance a good answer to "Can you pass the salt" is to pass the salt; in most contexts "Yes" is not a good answer, although "No" is better and "I'm afraid that I can't see it" is better yet. Or again, if a class was not offered last year, "The class was not offered last year" is a better answer to the question "How many students failed the class last year?" than "None" is.

Statistical NLP

Statistical natural language processing uses stochastic, probabilistic and statistical methods to resolve some of the difficulties discussed above, especially those which arise because longer sentences are highly ambiguous when processed with realistic grammars, yielding thousands or millions of possible analyses. Methods for disambiguation often involve the use of corpora and Markov models. The technology for statistical NLP comes mainly from Machine learning and Data Mining, both of which are fields of Artificial Intelligence that involve learning from data.

See also

• The fictional universal translator
• computational linguistics
• controlled natural language
• information retrieval
• natural language understanding
• latent semantic indexing

External links

• Survey of the State of the Art in Human Language Technology
• Natural Language Processing Group at the Johns-Hopkins University
• Stanford Natural Language Processing Group
• 2004 International Workshop on Natural Language Understanding and Cognitive Science

Implementations

• GATE: a Java Library for Text Engineering
• Natural Language ToolKit for Python - comprehensive tutorial