Please view explanation and answer below.Running head: Natural language processingNatural Language ProcessingLiterature ReviewNameDepartment of Computer and Information ScienceITM555 ITM CapstoneDr. Heather WegwerthJanuary 1, 20222Natural language processingAbstractNatural language processing (NLP) and its role in the near future is the essential subjectof this report. In the current day and age, technology is rapidly evolving to process an everincreasing amount of information. In the field of Natural Language Processing (NLP), this isparticularly evident, with a growing number of studies and applications being developed to dealwith the challenges posed by ever-larger and more complex datasets. The advancement oftechnology has greatly improved the way humans interact with machines. In the past, humanshad to learn how to use machines to get them to work. However, as technology advanced,machines began to learn how to understand and respond to human input. It is where naturallanguage processing (NLP) comes in. NLP is a rapidly growing field with many real-worldapplications. In the near future, NLP will become increasingly important as humans developmore intelligent and Human-like Artificial Intelligence (AI).3Natural language processingNatural Language Processing (NLP) And Its Role in The Near FutureNatural language processing is relevant to the broader academic discussion surroundingartificial intelligence and machine learning. NLP is a valuable tool for analyzing andunderstanding large amounts of natural language data (Lin et al., 2021). Natural languageprocessing is a field of computer science and linguistics concerned with the interactions betweencomputers and human (natural) languages to enhance communication. To properly understandand process human language, NLP systems need to be able to perform tasks such as textclassification, information extraction, machine translation, and question-answering.Due to the ever-growing demand for faster and easier ways to process and communicateinformation, an important area of research in computer science is developing ways to enablecomputers to analyze, understand and generate human language. This area of study, known asnatural language processing (NLP), plays a vital role in many promising future applications, suchas automatic machine translation, question answering, and information retrieval from speech ortext. However, many significant technical challenges must be overcome before these applicationscan be developed and deployed.The ultimate goal of NLP research is to build computer programs that can automaticallytranslate between different human languages, answer questions posed in natural language, andgenerate text or speech that sounds natural to humans. However, many significant technicalchallenges must be overcome before this can be achieved. In particular, more research is neededon ways to represent the underlying structure of human language, as well as on ways to generatetext or speech that is fluent and sounds natural to humans.4Natural language processingNLP technologies are used in various applications, including automatic (machine)translation, question answering, information retrieval from speech or text, and creating chatbots.Many of these applications are still in their early stages of development and are far from beingable to replace humans in performing these tasks (Lin et al., 2021). However, there has beensome success in developing NLP systems that can outperform humans in specific tasks, such asmachine translation of technical documents, answering questions from extensive collections oftexts, and intelligent search engines. NLP is a complex field that encompasses many differentsubfields, such as linguistics, artificial intelligence, cognitive science, and computer science. Italso ties strongly to other areas, such as psychology, anthropology, and sociology.Literature ReviewThis paper aims to provide an overview of the field of natural language processing,including its history, current state, and future direction. In addition, this paper will discuss thepotential applications of NLP technology and the challenges involved in its development. Thereis a long history of research in natural language processing, dating back to the early days ofcomputing. However, the field has seen significant growth and advancement in recent years dueto increased computational power and the availability of large data sets.First Main Point: Automatic SummarizationAutomatic summarization is reducing a text document with a computer program to createa summary that retains the most critical points of the original document. The original documentmay be a complete text or any size: a web page, a paragraph, a sentence, or even a single word.There are two types of automatic summarization: extractive and abstractive.First subtopic to support the main point: Extractive summarization5Natural language processingExtractive summarization is a technique for creating a summary by selecting basicsentences from the original text and copying them verbatim (Meera & Geerthik, 2022).Extractive methods are generally quick and easy to implement, but they often produce shorterand rougher summaries than those produced by abstractive methods.Second subtopic to support the main point: Abstractive summarizationAbstractive summarization is a technique for creating a summary by paraphrasing orrewriting the crucial ideas in the original text (Raharjana et al., 2021). Abstractive methods aregenerally more challenging to implement than extractive methods, but they often produce longerand smoother summaries than those produced by extractive methods.Second Main Point: Machine TranslationMachine translation is the process of translating a text from one language to another withthe help of a machine. There are two types of machine translation: statistical and rule-based.First subtopic to support the second main point: Statistical machine translationStatistical machine translation is a technique that relies on statistical models to translatetext from one language to another. This approach is generally faster and more accurate than rulebased machine translation but requires a large amount of training data.Second subtopic to support the second main point: Rule-based machine translationRule-based machine translation is a technique that relies on linguistic rules to translatetext from one language to another (Lin et al., 2021). This approach is generally slower and lessaccurate than statistical machine translation but requires less training data.Third Main Point: Named Entity Recognition6Natural language processingNamed entity recognition identifies named entities in text, such as people, places,organizations, and so on. Three main approaches to named entity recognition are rule-based,statistical, and hybrid.First subtopic to support the third main point: Rule-based approachesRule-based approaches rely on linguistic rules to identify named entities in text. Thisapproach is generally more accurate than statistical or hybrid approaches but is also more timeconsuming and expensive.Second subtopic to support the third main point: Statistical approachesStatistical approaches rely on statistical models to identify named entities in text. Thisapproach is generally less accurate than rule-based approaches but is also less time-consumingand expensive.Third subtopic to support the third main point: Hybrid approachesHybrid approaches combine rule-based and statistical approaches to identify namedentities in text. This approach is generally more accurate than rule-based or statistical approachesbut is also more time-consuming and expensive.CounterclaimsExample 1Natural language processing is not a reliable method of communication. There are severalreasons why natural language processing (NLP) is not a reliable method of communication. First,NLP systems are often based on statistical models, which are notoriously difficult to verify.Second, even when NLP systems produce accurate results, they can be challenging to interpret7Natural language processing(Saquete et al., 2020). Third, NLP systems often use language-specific rules that may not betransferable to other languages. Finally, NLP systems are usually designed for specific tasks ordomains and may not be adequate for different tasks or domains.Example 2Natural language processing is not effective for all types of communication. Naturallanguage processing (NLP) is not effective for all kinds of communication. For example, NLPsystems often have difficulty understanding irony, sarcasm, and other forms of non-literalcommunication. Additionally, NLP systems typically require large amounts of training data toproduce accurate results, making them impractical for many applications.NLP enhances communicationThe thesis statement for this paper indicates that natural language processing aims toenhance communication. It is a counterclaim to the first point that natural language processing isnot a reliable method of communication. The thesis statement is also a counterclaim to thesecond point that natural language processing is not effective for all types of communication.The thesis statement argues that natural language processing is a reliable method ofcommunication and is effective for all kinds of communication.ConclusionIn conclusion, natural language processing is a relevant and vital topic in computerscience and artificial intelligence. Current natural language processing methods are not yetadvanced enough to accurately and fluently translate all forms of human communication.However, with continued research and development in the field, these methods will likelycontinue to improve, making natural language processing an increasingly valuable tool for8Natural language processingbusinesses and individuals. Further research in this area is ne…

QUALITY: 100% ORIGINAL – NO PLAGIARISM

(USA, AUS, UK & CA PhD. Writers)

CLICK HERE TO GET A PROFESSIONAL WRITER TO WORK ON THIS PAPER AND OTHER SIMILAR PAPERS

The Best Custom Essay Writing Service

About Our Service

We are an online academic writing company that connects talented freelance writers with students in need of their services. Unlike other writing companies, our team is made up of native English speakers from countries such as the USA, UK, Canada, Australia, Ireland, and New Zealand.

Qualified Writers

Our Guarantees:

CLICK TO SUBMIT YOUR ORDER