Natural Language Processing Movie

Category: Entertainment

Presentation Description

No description available.


Presentation Transcript

Natural Language Processing(Question and Answer):

Natural Language Processing (Question and Answer) BY: Justin Parkansky Elma Bashir Ynhu Nguyen

What is Natural Language Processing? :

What is Natural Language Processing? A method to translate between computer and human languages. A method of getting a computer to understandably read a line of text without the computer being fed some sort of clue or calculation. NLP automates the translation process between computers and humans . The ultimate goal of NLP is to build software that will analyze, understand and generate human languages naturally, enabling communication with a computer as if it were a human.

History Of NLP:

History Of NLP NLP is incredibly old   Use of the computer for calculating artillery tables and code-breaking was less pressing for a few years after 1945- this gave Peace time gave researchers the opportunity to allow their imagination roam over new applications As a research idea- became popular in USA, UK, France and Soviet Union Wanted to translate document from war By mid 1960s, US funding of Machine Translation machine had cost the public purse $20 million Automatic Language Processing Advisory Committee (ALPAC) produced a report on the results of the funding and concluded that "there had been no machine translation of general scientific text, and none is in immediate prospect ". Histories suggest NLP virtually disappeared after ALPAC report True, there was much less NLP work But, there were significant developments in systems in the 15 years after the ALPAC report

Why Natural Language Processing? :

Why Natural Language Processing? Huge amounts of data Internet=at least 20 billion pages Intranet Applications for Processing large amounts of texts require NLP expertise Classify text into categories Index and search large texts Automatic translation Speech understanding Understand phone conversations Information extraction Extract useful information from resumes Automatic summarization Condense 1 book into 1 page Question answering Knowledge acquisition Text generations / dialogues

Natural Language :

Natural Language Natural language Refers to language spoken by people ex. English, Japanese, Hindi Natural Language Processing Applications that deal with natural language in a way or another

Question and Answering:

Question and Answering QA is an application area of computer science which attempts to build software systems that can provide accurate, useful answers to questions poised by human users in natural language Software system that provides exact answers to natural language questions for some range of topics Exact= contains just the info necessary to precisely answer the question intended by user Accuracy and ability to justify an answer increases with the amount of relevant info provided in the question QA systems rely on a deeper “understanding” of the intent of the question


RESOURCES USED TO ANSWER QUESTIONS Resources use can vary from Unstructured Data: web pages, blog posts Semi-Structured Data: Wikipedia Completely Structured Data: Facts mined form the web or Pre-existing Databases

Steps to Answer Questions:

Steps to Answer Questions Signal Processing : Takes spoken words as input and turns it into text Syntactic Analysis: G ets at the structure or grammar of the sentences Semantic Analysis: D eals with the meaning of words and sentences, the ways that words and sentences refer to elements in the world Pragmatics: C oncerns how the meaning of a sentence depends on its function in everyday life, that is, the larger context of the conversation and so forth, and so it too seems concerned with meaning

How Natural Language Questioning and Answering Works  :

How Natural Language Questioning and Answering Works   Ever try to search something specific on Google and it can’t seem to understand what you’re searching for? Does Google take your sentence and take each word and mix them up in different sentences throughout an article making it difficult to actually find what you’re looking for? Have you ever typed so fast that you accidently misspelled similar-sounding words? How can we deliver our message to a computer the same way we can to a human?

Natural Language Question & Answering: How it Works :

Natural Language Question & Answering: How it Works Takes Human-to-computer language and transforms it to Human-to-Human language. Technology can make search engines and programs more faster and accurate by understanding how a sentence is broken down by and how we intend to deliver it by looking and processing our Verbs Nouns Adjectives Misspellings

Natural Language Questioning & Answering: How it Works Examples :

Natural Language Questioning & Answering: How it Works Examples The search results break up the sentence into pieces and makes my question much harder to find. Google doesn’t know I’m asking a question Search results are spread out in chunks throughout the whole page Finding my answer is difficult and time consuming

Natural Language Questioning & Answering: How it Works Examples:

Natural Language Questioning & Answering: How it Works Examples If I ask a human the same question I will get a direct answer Example: “What are the best majors to take at Temple University?” Answer: “Accounting, Finance, Business Management” Computer language doesn’t interpret the same way as a human can. Tell a computer, “Flying Planes can be dangerous” Is the pilot at risk or the people on the ground? Is “can” referred to a verb or noun? Plane can refer to an “airplane” “geometric object” “woodworking tool” A human would be able to construct the sentence but a computer sometimes cannot. Natural Language helps knowledge-engineered and statistical/machine-learning techniques to disambiguate and respond to natural language input as if you are speaking to a human not a computer. The goal: make language universal between both

Technology Prevalent in Marketplace:

Technology Prevalent in Marketplace Apple iPad puts tablets and multitouch at the center of changes to consumer electronics and PCs. Speech , natural language processing, gestures and haptics augment tablet interfaces leading to new usages and markets . The iPad has created a transformational change in how people interact with computers with the use of NLP E xamples of QA system Siri: One can easily pose a question to siri and she will have an immediate response for it Google Talk Google Wave- ex: When typing many words and sentences in a small period of time sometimes misspelled homophones can be accidentally typed. We should met in the break out room vs. We should meet in the breakout room. The NLP automatically knows what the person is talking about and corrects to the proper grammar


ADVANTAGES Fast Response - users are able to ask questions about any subject and get a direct response within seconds Easy to Understand- system provides answers to the questions in natural language, it is clearly explained and easily understood by humans Relevant Information- system provides exact answers to the questions, no unnecessary or irrelevant information Accuracy - accuracy of the answers increases with the amount of relevant information provided in the question


DISADVANTAGES Complex Query Language- the system may not be able to provide the correct answer if the question is poorly worded or ambiguous Complex Questions- questions that require complex reasoning tend to be more difficult to answer Limited Ability - system is built for a single and specific task only, it is unable to adapt to new domains and problems due to its limited functions Lack of User Interface/Usability - the system lacks features that allow users to further interact with the system

Natural Language Processing In Healthcare :

Natural Language Processing In Healthcare Promises to reduce costs and improve quality of healthcare providers By processing text directly with computer applications, an organization can leverage: Wealth of available patient info in clinical documentation to improve communication between caregivers Reduce the cost of working with clinical documentation automate the coding and documentation improvement processes

Normalization :

Normalization In the world of health care, this is an absolutely essential step in NLP development and one in which ontology—the ability to define what something is—plays a vital role . Consider how many ways a term like “COLD” can be interpreted in a clinical environment: – COLD can be an acronym for Chronic Obstructive Lung Disease – A patient in shock can tell an ER nurse that he feels cold ( physical temperature) – A mother can call the family doctor and describe her child’s symptoms as indicative of a very bad “cold” Maintain a huge lists of words that look and sound the same but have different meanings Such a dictionary should also include all possible abbreviations, variants, alternative expressions, and even misspellings and slang terminology used to describe a single concept

Case Study- Cleveland Clinic:

Case Study- Cleveland Clinic T he amount of medical information available is doubling every five years and much of this data is unstructured - often in natural language . physicians simply don't have time to read every journal that can help them keep up to date with the latest advances - 81 percent report that they spend five hours per month or less reading journals . Watson addresses these complex problems, helping the doctor — and patient — make more informed and accurate decisions Watson uses natural language capabilities: For example, a physician can use Watson to assist in diagnosing and treating patients. First the physician might pose a query to the system, describing symptoms and other related factors. Watson begins by parsing the input to identify the key pieces of information. The system supports medical terminology by design, extending Watson's natural language processing capabilities. Watson will then provide a list of potential diagnoses 

Visually summarizes the multiple components of an NLP engine and the steps in which unstructured text is handled.:

Visually summarizes the multiple components of an NLP engine and the steps in which unstructured text is handled.

Works Cited :

Works Cited Janssen, Corry. "Natural Language Processing (NLP)."  Techopedias . N.p ., n.d. Web. 24 Nov. 2013. < >. "SEM1A5 - Part 1 - A Brief History of NLP."  SEM1A5 - Part 1 - A Brief History of NLP . N.p ., n.d. Web. 24 Nov. 2013. < >. Ferrucci , David, et al. “Towards the Open Advancement of Question Answering Systems.” IBM Research Division , (2009): 1-29. Web. 23 November 2013. <http ://>. Hirschman, L., and Gaizauskas , R. “Natural Language Question Answering: The View from Here .” Natural Language Engineering, (2001): 275-300. Web. 24 November 2013. http :// "Overview." Natural Language Processing . Microsoft Research, n.d. Web. 25 Nov. 2013. < />. "Introduction to Natural Language Processing." The Mind Project . CCSI, 2006. Web. 25 Nov. 2013 . <>. Lazerowitz , Ross. "What Is Natural Language Processing?" Information Space What Is Natural Language Processing Comments . School of Information Studies: Syracuse University, 11 May 2012. Web. 25 Nov. 2013. < />. "Auto-Coding and Natural Language Processing."  3M Health Information Systems . N.p ., n.d. Web. 25 Nov. 2013. <>. "Watson Is Helping Doctors Fight Cancer."  IBM Watson . IBM, n.d. Web. 25 Nov. 2013. < >. McIntyre, Angela. "IPad and Beyond: What the Future of Computing Holds."  Gartner . N.p ., 30 Sept. 2011. Web. 24 Nov. 2013. <>.

authorStream Live Help