Natural Language Processing

An example of Pragmatic Analysis

"Do you know what time it is?" It does not mean the speaker is asking you the time. The speaker is referring to lateness.

Ambiguity

1) Computational linguists are obsessed with this. 2) This is a fundamental problem of computational linguistics 3) Resolving this is a crucial goal

NLP Applications

1) Intelligent computer systems 2) NLU interfaces to databases 3) Computer aided instruction 4) Information retrieval 5) Intelligent Web searching

These are the steps to Text Processing:

1) Lexical: tokenization, part of speech, head, lemmas 2) Parsing and chunking 3) Semantic tagging: semantic role, word sense 4) Certain expressions: named entities 5) Discourse: coreference, discourse segments

What is Word Sense Resolution?

1) Many words have many meanings or senses. 2) We need to resolve which of the senses of an ambiguous word is invoked in a particular use of the word.

The Steps in NLP:

1) Morphology 2) Syntax 3) Semantics 4) Pragmatics 5) Discourse

Speech Processing is

1) Phonetic transcription 2) Segmentation (punctuations) 3) Prosody

An example of Discourse Integration

1) Sarah had a yellow balloon. 2) John wanted it.

Syntactic Analysis

1) This is concerned with the construction of sentences. 2) Indicates how the words are related to each other. 3) Syntax tree is assigned by a grammar and a lexicon.

Definition of Semantic Analysis

1) This is concerned with the meaning of language. 2) The first step in this process is to look up the individual word in the dictionary and extract tits meaning.

Morphological Analysis

1) This is the structure of words. 2) Various form of basic word. 3) Make more words from less.

Definition of Pragmatic Analysis

1) Understanding the text & dialogues. 2) It derives Knowledge from external commonsense information.

Reasons why NLP is difficult:

1)Different ways of Parsing a sentence 2)Word category ambiguity 3)Word sense ambiguity 4)Words can mean more than their sum of parts. (NY Times) 5)Imparting world knowledge is difficult ("the red pen ate the green apple")

More NLP Applications

6) Data mining 7) Machine translation 8) Speech recognition 9) Natural language generation 10) Question answering

More reasons why NLP is difficult:

6) Fictitious worlds ("people on the moon can fly") 7) Defining scope ("people like ice-cream," does this mean all people like ice cream?) 8) Language is changing and evolving 9) Complex ways of interaction between the kinds of knowledge 10) exponential complexity at each point in using the knowledge

Computers_______

Analyze, understand, generate, natural language.

Definition of Syntactic Analysis

Assigning a syntactic and logical form to an input sentence

Pragmatics

Concerns how sentences are used in different situations and how use affects the interpretation of the sentence.

Discourse

Concerns how the immediately preceding sentences affect the interpretation of the next sentence.

Syntax

Concerns how words are put together to form correct sentences and what structural role each word has.

Morphology

Concerns the way words are built up from smaller meaning bearing units. (come(s),co(mes))

Semantics

Concerns what words mean and how these meanings combine in sentences to form sentence meanings.

Natural language understanding

Is a subtopic of natural language processing in artificial intelligence that deals with machine reading comprehension

Tokenization, part of speech, head, lemmas

Lexical

Semantic role, word sense

Semantic tagging

Another word for parsing is

Syntactic Analysis

Definition of Discourse Integration

The meaning of an individual sentence is depend on the previous sentence.

An example of Semantic Analysis

The sentence "you have a colorless purple idea...." would rejected because colorless & purple makes no sense.

What is Natural language processing (NLP)?

This is a field of computer science, artificial intelligence and computational linguistics concerned with the interactions between computers and human (natural) languages, and, in particular, concerned with programming computers to fruitfully process large natural language corpora.