What is Natural Language Processing and It’s Techniques.
Natural language processing is a field of artificial intelligence and linguistics. It focuses on developing systems that allow computers to communicate with people using everyday language.
Natural language processing (NLP) can be defined as the automatic (or semi-automatic) processing of human language.
Natural language processing is the engineering of systems that processes or analyzes written or spoken natural language.
Natural language processing is a significant area of AI because a computer would be considered intelligent if it can understand the commands given in natural language.
The main task of natural language processing is to deal with the interactions between computers and human languages. This in itself is an entire separate area of computer science, which is called human-computer interaction.
The main problems that face people working on natural enabling language processing are summed up in the task of natural language understanding, which means computers to understand in a certain way what human language input is meant to convey.
The most recent natural language processing ideas involve machine learning, and more specifically statistical machine learning. Machine learning is also a branch of artificial intelligence and it concerns the construction and study of systems that can learn from data.
Some of the most common topics of research in natural language processing include: machine translation, which involves translating the input text from one human language to another. This is one of the hardest problems and requires a very wide range of knowledge types in order for it to be solved.
There is also automatic summarization, which involves producing a readable summary of a passage or a text. This is an often used application of natural language processing. There is discourse analysis, and it includes a lot of tasks such as identifying the discourse structure of text, and recognizing and classifying speech acts in a chunk of text. Other commonly known applications are: conference resolution, name entity recognition, natural language generation, natural language understanding, optical character recognition, question answering, speech recognition and sentiment analysis.
This is just a small portion of what natural language processing involves. And, the span of what natural language processing can become in the future is very wide. One of the most difficult problems still facing professionals in the field is human-level natural language processing which if solved is equivalent to solving the central artificial intelligence problem that is making computers as intelligent as people.
The future of natural language processing is therefore tied closely to the development of artificial intelligence. As natural language understanding improves, future computers will have the ability to obtain data and learn online and apply that in the real world. Combined with natural language generation, computers will soon be more capable taking in and giving out instructions.
Goal of NLP
The goal of NLP is to accomplish human-like language processing i.e. the goal of NLP is to design and build a computer system that will analyze, understand, and generate natural human-languages.
A complete NLP system would be able to:
1. Translate of one human-language text to another.
2. Generate human-language text such as fiction, manuals, and general descriptions.
3. Interface to other systems such as databases and robotic systems thus enabling the use of human language type commands and queries.
4. Answer questions about the contents of the text.
5. Understand human-language text to provide a summary or to draw conclusions.
There are more practical goals for NLP, many related to the particular application for which it is being utilized.
Natural Language Processing techniques
1. Pattern Matching.
2. Syntactically-driven Parsing
3. Semantic Grammars
4. Case frame instantiation
5. Robust Parsing
1. Pattern Matching:
This technique involves interpreting input utterances as a whole, rather than building up their interpretation by combining the structure and meaning of words or other lower-level constituents. The approach is thus wholistic rather than constructive. With this approach, the interpretations are obtained by matching patterns of words against the input utterance. Associated with each pattern is an interpretation, so that the derived interpretation is the one attached to the pattern that matched.
2. Syntactically-driven Parsing:
This technique deals with the ways that words can fit together to form higher level units such as phrases, clauses and sentences. Syntactically driven parsing means interpretation of larger groups of words are built up out of the interpretation of their syntactic constituent words or phrases. In a way this is the opposite of pattern matching as here the interpretation of the input is done as a whole.
3. Semantic Grammars:
Natural language analysis based on semantic grammar is similar to syntactically driven parsing except that in semantic grammar the categories used are defined semantically and syntactically. Thus, here semantic grammar is also involved. However, this technique only works properly in restricted domains. Thus, it is a technique useful only for applied natural language processing. not for general NLP.
4. Case frame instantiation:
Case frame instantiation is one of the major parsing techniques under active research today. It has some very useful computational properties such as its recursive nature and its ability to combine bottom-up recognition of key constituents with top-down instantiation of less structured constituents.
5. Robust Parsing
Any natural language interface which is used in a practical application with a multitude of users must be able to handle input that is outside its grammar or expectations in various ways. Methods of robust parsing are under active investigation at the moment with the chief outstanding problem being the coordination of multiple, independent, construction-specific parsing strategies on the same input.
VIsit our site for more post:- www.bootpoot.tech