Archive

Archive for the ‘Natural Language Processing’ Category

Statistical NLP

September 4th, 2010 No comments

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. Statistical NLP comprises all quantitative approaches to automated language processing, including probabilistic modeling, information theory, and linear algebra. 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.

Ambiguity and Disambiguation in NLP

September 4th, 2010 1 comment

The biggest problem in natural language processing is that most utterances are ambiguous. Following section describes different type of ambiguities

Lexical ambiguity

The lexical ambiguity of a word or phrase consists in its having more than one meaning in the language to which the word belongs. “Meaning” hereby refers to whatever should be captured by a good dictionary. For instance, the word “bank” has several distinct lexical definitions, including “financial institution” and “edge of a river”. Another example is as in apothecary. You could say, “I bought herbs from the apothecary.” This could mean you actually spoke to the apothecary (pharmacist) or went to the apothecary (drug store).

Syntactic ambiguity

Syntactic ambiguity is a property of sentences, which may be reasonably interpreted in more than one way, or reasonably interpreted to mean more than one thing. Ambiguity may or may not involve one word having two parts of speech or homonyms.

Syntactic ambiguity arises not from the range of meanings of single words, but from the relationship between the words and clauses of a sentence, and the sentence structure implied thereby. When a reader can reasonably interpret the same sentence as having more than one possible structure, the text is equivocal and meets the definition of syntactic ambiguity.

Semantic ambiguity

Semantic ambiguity arises when a word or concept has an inherently diffuse meaning based on widespread or informal usage. This is often the case, for example, with idiomatic expressions whose definitions are rarely or never well defined, and are presented in the context of a larger argument that invites a conclusion.

For example, “You could do with a new automobile. How about a test drive?” The clause “You could do with” presents a statement with such wide possible interpretation as to be essentially meaningless. Lexical ambiguity is contrasted with semantic ambiguity. The former represents a choice between a finite number of known and meaningful context-dependent interpretations. The latter represents a choice between any numbers of possible interpretations, none of which may have a standard agreed-upon meaning. This form of ambiguity is closely related to vagueness.

Referential ambiguity

If it is unclear what a referring expression is referring to, then the expression is referentially ambiguous. For example, a pronoun is a referring expression such as “it”, “he”, “they”, etc. You might point to a famous basketball player and say, “he is rich”, and here “he” refers to the player. Nevertheless, if it is not clear whom you are pointing to, then we might not know to whom the pronoun refers, and so might not be able to determine whether you are saying something true. Similarly, without further information, a statement such as “Ally hit Georgia and then she started bleeding” is also referentially ambiguous. This is because it is not clear whether it is Ally or Georgia, or some third person, who started to bleed.

Referential ambiguity can also arise if you are talking about a group using an expression such as “every”. People are often fond of making generalizations, such as “everyone thinks that democracy is a good thing.” However, is it true that absolutely everyone in the world thinks so? Of course not. Therefore, who are we talking about here? There is no ambiguity if the context makes it clear which group of people we are talking about. Otherwise, there is a need to clarify.

Sometimes the context makes it clear which group of people a speaker is referring to. A teacher taking attendance might say, “Everyone is here.” Of course, the teacher is not saying that every human being in the whole world is here. He or she is likely to be talking about the students in the class.

Pragmatic ambiguity

All languages depend on words and sentences in constructing meaning. However, one of the fundamental facts about words and sentences is that many of them in our languages have more one meaning. Therefore, ambiguity may occur when an utterance can be understood in two or more distinct senses. Kess and Hoppe even say in Ambiguity in Psycholinguistics, “Upon careful consideration, one cannot but be amazed at the ubiquity in language. English, as a language is no exception to it. Since Ambiguity is not a new topic, many researches have been made in this field. In the west, ambiguity can be traces back to the sophism of ancient Greek philosophy. However, previous researches are mainly concerned with phonological ambiguity, lexical ambiguity and grammatical ambiguity. However, the word “pragmatics” was first put forward in 1930s by Charles Morris and the category of pragmatic ambiguity was not explored until the 1970s. So researches on pragmatic ambiguity are still insufficiently thorough, for example, its definition, characteristics, category, functions and understanding still need further study.

Sub Problems of NLP

September 4th, 2010 1 comment
  • Speech segmentation

In most spoken languages, the sounds representing successive letters blend into each other, so the conversion of the analog signal to discrete characters can be a very difficult process. Also, in natural speech there are hardly any pauses between successive words; the location of those boundaries usually must take into account grammatical and semantic constraints, as well as the context.

  • Text segmentation

Some written languages like Chinese, Japanese and Thai do not have single-word boundaries either, so any significant text parsing usually requires the identification of word boundaries, which is often a non-trivial task.

  • Part-of-speech tagging
  • 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 ambiguous, i.e. there are often multiple possible parse trees for a given sentence. Choosing the most appropriate one usually requires semantic and contextual information. Specific problem components of syntactic ambiguity include sentence boundary disambiguation.

  • 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

A sentence can often be considered an action by the speaker. The sentence structure alone may not contain enough information to define this action. For instance, a question is sometimes the speaker requesting some sort of response from the listener. The desired response may be verbal, physical, or some combination. For example, “Can you pass the class?” is a request for a simple yes-or-no answer, while “Can you pass the salt?” is requesting a physical action to be performed. It is not appropriate to respond with “Yes, I can pass the salt,” without the accompanying action (although “No” or “I can’t reach the salt” would explain a lack of action).

Natural Language Processing

September 4th, 2010 No comments

Natural Language processing (NLP) is a field of computer science and linguistics concerned with the interactions between computers and human (natural) languages. In theory, natural language processing is a very attractive method of human-computer interaction. 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.

NLP has significant overlap with the field of computational linguistics, and is often considered a sub-field of artificial intelligence.