First phase (machine translation phase) - From the late 1940s to the late 1960s
The work carried out in this phase mainly focused on translation automatic (MT). This phase was a time of enthusiasm and optimism.
Now let's see what the first phase contained -
Research on NLP began in the early 1950s after the Booth & Richens investigation and Weaver's memorandum on machine translation in 1949.
1954 was the year in which limited experience in machine translation of the Russian in English demonstrated in theGeorgetown-IBM experience.
In the same year, the publication of the journal MT (Machine Translation) began.
The first International Conference on Machine Translation (MT) was held in 1952 and the second was held in 1956.
In 1961, the work presented to Teddin The gton international conference on machine translation of languages and analysis of applied languages was the culmination of this phase.
Second phase (AI-influenced phase) - late 1960s to late 1970s
In this phase, the work carried out was mainly linked to knowledge of the world and its role in the construction and manipulation of representations of meaning. Therefore, this phase is also called IA flavor phase.
The phase had in it, the following -
At the beginning of 1961, work began on the processing problems et data or knowledge base construction. This work was influenced by AI.
In the same year, a BASEBALL question-and-answer system was also developed. Entry to this system was restricted and the language processing involved was straightforward.
A very advanced system was described in Minsky (1968). This system, compared to the BASEBALL question answering system, has been recognized and provided for the need for knowledge base inference to interpret and respond to language input.
Third Phase (Grammatico-logical Phase) - Late 1970s to late 1980s
This phase can be described as the grammatic phase -logic. Due to the failure of building practical systems in the last phase, researchers turned to using logic for knowledge representation and reasoning in AI.
The third phase cocontained the following elements -
The grammatical-logical approach, towards the end of the decade, helped us with powerful sentence processors to general purpose like SRI's Core Language Engine and Discourse Representation Theory, which provided a means of a more expansive speech.
In this phase we got practical resources and tools such as analyzers eg Alvey Natural Language Tools as well as more operational and commercial systems eg. for the database query.
Lexicon work in the 1980s also pointed in the direction of a classical grammatical-log approach.
Fourth phase (lexical and corpus phase) - The 1990s
We can describe this as a lexical and corpus phase. The phase had a lexicalized approach to grammar that emerged in the late 1980s and became an influencegrowing. There has been a revolution in natural language processing during this decade with the introduction of machine learning algorithms for language processing.
Study of human languages
Language is a crucial element for human life and also the most basic aspect of our behavior. We can experience this mainly in two forms - written and oral. In written form, it is a way to pass our knowledge from one generation to the next. In the oral form, it is the main way for human beings to coordinate with each other in their daily behavior. The language is studied in various academic disciplines. each discipline comes with its own set of problems and a solution to solving them.
Consider the following table to understand this -
| Discipline || Problems || Tools |
How do they expressions and sentences be formed with words?
What limits the possible meaning of a sentence?
Intuitions on the right formation and the meaning.
Mathematical model of structure. For example, to model the theoretical semantics, the theory of formal language.
How humans can identify sentence structure?
How to identify the meaning of words?
When does understanding take place?
Experimental techniques mainly for measuring the performance of human beings.
Statistical analysis of observations.
How words and sentences acquire do they make sense?
How are objects identifiedés by words?
What is the meaning?
Natural language Use argumentation using intuition.
Mathematical models like logic and model theory.
How can we identify the sentence structure
How to model knowledge and reasoning?
How can we use language to accomplish specific tasks?
Formal models of representation and reasoning.
AI techniques such as search and representation methods.
Ambiguity and uncertainty in language
Ambiguity, generally used in natural language processing, can be considered as the ability to be understood in more than one way. Simply put, we can say that ambiguity is the ability to bere understood in more than one way. The natural language is very ambiguous. NLP has the following types of ambiguities -
The ambiguity of a single word is called lexical ambiguity. For example, treating the word money as a noun, adjective, or verb.
This type of ambiguity occurs when a sentence is parsed in different ways. For example, the sentence "The man saw the girl with the telescope". It is ambiguous whether the man saw the girl carrying a telescope or whether he saw her through his telescope.
This type of ambiguity occurs when the meaning of words themselves can be misinterpreted. In other words, semantic ambiguity occurs when a sentence contains an ambiguous word or sentence. For example, the sentence "The car hit the pole while it was moving" has a semantic ambiguity because the interpretationsons can be “The car, while moving, hit the post” and “The car hit the post while the post was moving”.
This type of ambiguity arises from the use of anaphoric entities in speech. For example, the horse climbed the hill. It was very steep. He quickly got tired. Here, the anaphoric reference to "It" in two situations causes an ambiguity.
This type of ambiguity refers to the situation where the context of a sentence gives it multiple interpretations. Simply put, we can say that pragmatic ambiguity arises when the statement is not specific. For example, the phrase "I love you too " can have multiple interpretations like I love you (just like you love me), I like you (just like someone from). 'other dose).
The following diagram shows the phases or logical steps in the treatment of lnatural angage -
This is the first phase of NLP. The purpose of this phase is to "un-comfortable" can be "un-easy" .
This is the second phase of NLP. The goal of this phase is twofold: to check that a sentence is well formed or not and to break it down into a structure that shows the syntactic relationships between the different words. For example, a sentence like "School goes to boy " would be rejected by a parser or parser.
This is the third phase of NLP. The purpose of this phase is to derive an exact meaning, or you can say the meaning from the dictionary.e from text. The meaning of the text is checked. For example, a semantic analyzer would reject a sentence like "Hot ice-cream".
This is the fourth phase of NLP. Pragmatic analysis simply adjusts the real objects / events, which exist in a given context with object references obtained in the last phase (semantic analysis). For example, the sentence "Put the banana in the basket on the shelf" can have two semantic interpretations and a pragmatic analyzer chooses between these two possibilities.