artificial intelligence Chapter 6 - NLP.pdf
- 1. Wolaita Sodo University School of Informatics Department of Computer Science Course title: Introduction to Artificial Intelligence Compiled by: Eyob S. (MSc)
- 2. Chapter 6 Natural Language Processing (NLP)
- 3. Introduction • Language is a means of communication which we use between two entities. • Natural language is a language used by human being. • NLP stands for Natural Language Processing, which is a part of Computer Science, Human language, and Artificial Intelligence. • Natural language processing (NLP) is the ability of a computer program to understand human language as it's spoken and written referred to as natural language. • It is the technology that is used by machines to understand, analyze, manipulate, and interpret human's languages. • It helps developers to organize knowledge for performing tasks such as translation, automatic summarization, Named Entity Recognition (NER), speech recognition, relationship extraction, and topic segmentation. • The field of NLP is primarily concerned with getting computers to perform useful and interesting tasks with human languages.
- 4. Forms of Natural Language • The field of NLP is primarily concerned with getting computers to perform useful and interesting tasks with human languages. • The field of NLP is secondarily concerned with helping us come to a better understanding of human language. • Processing of natural language plays an important role in various systems. A robot, it is used to perform as per your instructions. The input/output of a NLP system can be: • written text • speech
- 5. Why NLP is difficult? • Natural language is extremely rich in form and structure, and very ambiguous. • How to represent meaning, • Which structures map to which meaning structures. • NLP is difficult because ambiguity and uncertainty exist in the language. Ambiguity: means that the same word, phrase, or sentence can have different meanings depending on the context, the speaker, or the listener. There are the following three ambiguity:- 1. Lexical Ambiguity • Lexical Ambiguity exists in the presence of two or more possible meanings of the sentence within a single word. Example: • Kuku is looking for a match. • In the above example, the word match refers to that either Kuku is looking for a partner or Kuku is looking for a match. (Cricket or other match).
- 6. Cont… 2. Syntactic Ambiguity • In NLP, syntactic ambiguity refers to a situation where a sentence can be interpreted in multiple ways due to its grammatical structure, meaning the same sequence of words can be parsed differently, leading to different meanings depending on how the words are grouped together. Example: “The man saw the girl with the telescope”. It is ambiguous whether the man saw the girl carrying a telescope or he saw her through his telescope. 3. Referential Ambiguity • Pronoun usage: this is the most common cause of referential ambiguity, where pronouns like "he," "she," or "it" could refer to different people or things mentioned earlier in the text. • Example: "John met Mary and Tom. He was very happy." Here, "He" could refer to either John, Mary, or Tom.
- 7. Knowledge of Language • Phonology – concerns how words are related to the sounds that realize them. • Morphology – concerns how words are constructed from more basic meaning units called morphemes. A morpheme is the primitive unit of meaning in a language. • Syntax – concerns how can be put together to form correct sentences and determines what structural role each word plays in the sentence and what phrases are subparts of other phrases. • Semantics – concerns what words mean and how these meaning combine in sentences to form sentence meaning. The study of context-independent meaning. • 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. • World Knowledge – includes general knowledge about the world. What each language user must know about the other’s beliefs and goals.
- 8. Applications of NLP 1. Question Answering • Question answering focuses on building systems that automatically answer the questions asked by humans in a natural language.
- 9. Cont… 2. Spam Detection • Spam detection is used to detect unwanted e-mails getting to a user's inbox.
- 10. 3. Sentiment Analysis • Sentiment Analysis is also known as opinion mining. • Sentiment analysis is an application of natural language processing (NLP) technologies that train computer software to understand text in ways similar to humans. • It is used on the web to analyze the attitude, behaviour, and emotional state of the sender. • This application is implemented through a combination of NLP (Natural Language Processing) and statistics by assigning the values to the text identify the mood of the context (happy, sad, angry, etc.). Cont…
- 11. 4. Machine Translation • Machine translation is used to translate text or speech from one natural language to another natural language. Cont…
- 12. 5. Spelling correction • Microsoft Corporation provides word processor software like MS-word, PowerPoint for the spelling correction. Cont…
- 13. 6. Speech Recognition • Speech recognition is used for converting spoken words into text. 7. Chatbot • Implementing the Chatbot is one of the important applications of NLP. • It is used by many companies to provide the customer's chat services. Cont…
- 14. 8. Information extraction • Information extraction is one of the most important applications of NLP. • It is used for extracting structured information from unstructured or semi-structured machine-readable documents. 9. Natural Language Understanding (NLU) • It converts a large set of text into more formal representations such as first-order logic structures that are easier for the computer programs to manipulate representations of the natural language processing. Cont…
- 15. Advantages of NLP • NLP helps users to ask questions about any subject and get a direct response within seconds. • NLP offers exact answers to the question means it does not offer unnecessary and unwanted information. • NLP helps computers to communicate with humans in their languages. • It is very time efficient. • Most of the companies use NLP to improve the efficiency of documentation processes, accuracy of documentation, and identify the information from large databases.
- 16. Disadvantages of NLP • NLP may not show context • NLP is unpredictable because of its inherent reliance on the complexities of human language, including ambiguity, context-dependent meanings. • Complexity: NLP is a complex field, and it can be difficult to develop NLP systems that are accurate and scalable. • Data requirements: NLP systems require large amounts of data to train.
- 17. Natural Language Interaction • Natural language interaction (NLI) is an interaction style that allows users to interact with computers in a humanlike conversational way. • Through NLI, users can converse with computers just like they do with other humans. • Natural language is the way people communicate with each other. • Increasingly known as conversational AI, NLI allows technology to understand complex sentences containing multiple pieces of information and more than one request. It can then react accordingly, creating value and enhancing the user experience.
- 18. Computer vision and Image processing • Computer vision: is a subfield of artificial intelligence that enables machines to interpret and understand visual information from the world, much like human visual system. • It deals with acquiring, processing, analyzing, and making sense of visual data such as digital images. • It is one of the most compelling types of artificial intelligence that we regularly implement in our daily routines.
- 19. Cont… • Image processing: involves manipulating and analyzing images to enhance their quality, extract features, or recognize patterns. • Traditional image processing techniques rely on predefined rules and algorithms to perform specific tasks, such as edge detection, image segmentation, or object recognition. • However, these techniques often face limitations when dealing with complex and diverse visual data. • Modern image processing techniques…..
- 20. Case study: Sentiment Analysis, speech recognition, Chatbot Reading Assignment
- 21. Chapter 7 Robotic Sensing and Manipulation
- 22. Introduction to robotics What are Robots? • Robotics is the term used in artificial intelligence that deals with a study of creating intelligent and efficient robots. • Robots are multifunctional, re- programmable, automatic industrial machine designed for replacing human in hazardous work. • The word robot was firstly introduced to public by Czech writer Karel Capek in his play Rossum's Universal Robots (R.U.R), published in 1920. • The play begins with a factory that makes artificial people known as robots.
- 23. Cont… Objective • The aim of the robot is to manipulate/work the objects by perceiving, moving, picking, modifying the physical properties of object. Aspects of Robotics • The robots have electrical components for providing power and control the machinery. • They have mechanical construction, shape, or form designed to accomplish a particular task. • It contains some type of computer program that determines what, when and how a robot does something.
- 24. How Do Robots Work? • Some robots are pre-programmed to perform specific functions, meaning they operate in a controlled environment where they do simple. • Other robots are autonomous, operating independently of human operators to carry out tasks in open environments. • In order to work, they use sensors to perceive the world around them, and then employ decision-making structures (usually a computer) to take the optimal next step based on their data and mission. • But although robots vary in how they sense, compute, and act, they all operate in a similar way: Their sensors feed measurements to a controller or computer, which processes them and then sends control signals to motors and actuators.
- 25. Sensing • Sensors provide a robot with stimuli in the form of electrical signals that are processed by the controller and allow the robot to interact with the outside world. • Common sensors found within robots include video cameras that function as eyes, photoresistors that react to light and microphones that operate like ears. • These sensors allow the robot to capture its surroundings and process the most logical conclusion based on the current moment and allows the controller to relay commands to the additional components.
- 26. Types of Robot Sensors • There are different type of sensors are available to choose from and the characteristics of sensors are used for determining the type of sensor to be used for particular application. Light Sensor • Light sensor is a transducer used for detecting light and creates a voltage difference equivalent to the light intensity fall on a light sensor. Proximity Sensor • Proximity sensor can detect the presence of nearby object without any physical contact. The working of a proximity sensor is simple. Sound Sensor • Sound sensors are generally a microphone used to detect sound and return a voltage equivalent to the sound level. Using sound sensor a simple robot can be designed to navigate based on the sound receives.
- 27. Cont… Temperature Sensor • Temperature sensors are used for sensing the change in temperature of the surrounding. • It is based on the principle of change in voltage difference for a change in temperature this change in voltage will provide the equivalent temperature value of the surrounding. Acceleration Sensor • Acceleration sensor is used for measuring acceleration. An accelerometer is a device used for measuring acceleration.
- 28. Robot Manipulation • Robot manipulation is the ability for a robot to interact physically with objects in the world and manipulate them towards completing a task. • Robotic manipulation refers to the ways robots interact with the objects around them: grasping an object, opening a door, packing an order into a box. • All these actions require robots to plan and control the motion of their hands and arms in an intelligent way.
- 29. Human-Robot Interaction • Human Robot Interaction (HRI) is the study of interactions between humans and robots. • Human robot interaction is a multidisciplinary field with contributions from human computer interaction, artificial intelligence, robotics, natural language processing, design, others.
- 30. Cont… • Recent advances in robotic technology are bringing about robots better suited to perform tasks and applications in which robots are interacting directly with people in their everyday environments, both at home and in the workplace. • Human-robot interaction (HRI) is beneficial because robots have been shown to deliver an emotional response to humans and humans find robots engaging. • Additionally, robots can integrate into everyday settings without difficulty and can be perceived by humans as active social agents, meaning they can complete the programmed tasks with total control, independence, and intentionality. • With HRI, a user’s experience of interaction varies from person to person and is influenced by many factors such as physical context of the environment, cultural context, thoughts and feelings toward the robot, and social nature.
- 31. Autonomous Robotic Systems What are Autonomous Robots? • True autonomous robots are intelligent machines that can perform tasks and operate in an environment independently, without human control or intervention. • This level of autonomy gives the workforce the ability to dangerous or dirty tasks to the robot so humans can spend more time doing the interesting, engaging, and valuable parts of their job. • Each robot has a different level of autonomy. These levels range from human-controlled bots that carry out tasks to fully-autonomous bots that perform tasks without any external influences.
- 32. Types of Robotics Humanoid Robots • Humanoid robots are robots that look like or mimic human behavior. These robots usually perform human-like activities (like running, jumping and carrying objects), and are sometimes designed to look like us. Cobots • Cobots, or collaborative robots, are robots designed to work alongside humans. These robots prioritize safety by using sensors to remain aware of their surroundings, executing slow movements and terminating actions when their movements are obstructed. Cobots typically perform simple tasks, freeing up humans to address more complex work. Industrial Robots • Industrial Robots automate processes in manufacturing environments like factories and warehouses. Possessing at least one robotic arm, these robots are made to handle heavy objects while moving with speed and precision.
- 33. Cont… Medical Robots • Medical Robots assist healthcare professionals in various scenarios and support the physical and mental health of humans. These robots rely on AI and sensors to navigate healthcare facilities, interact with humans and execute precise movements. Agricultural Robots • Agricultural Robots handle repetitive and labor-intensive tasks, allowing farmers to use their time and energy more efficiently. These robots also operate in greenhouses, where they monitor crops and help with harvests. Agricultural robots come in many forms, ranging from autonomous tractors to drones that collect data for farmers to analyze. Software Bots • Software bots, or simply ‘bots,’ are computer programs which carry out tasks autonomously. They are not technically considered robots. One common use case of software robots is a chatbot, which is a computer program that simulates conversation both online and over the phone and is often used in customer service scenarios. • Chatbots can either be simple services that answer questions with an automated response or more complex digital assistants that learn from user information.
- 34. Robotics Applications • Beginning as a major boon for manufacturers, robotics has become a mainstay technology for a growing number of industries. Manufacturing • Industrial robots can assemble products, sort items, perform welds and paint objects. They may even be used to fix and maintain other machines in a factory or warehouse. Healthcare • Medical robots transport medical supplies, perform surgical procedures and offer emotional support to those going through rehabilitation. Companionship • Social robots can support children with learning disabilities and act as a therapeutic tool for people with dementia. They also have business applications like providing in-person customer service in hotels and moving products around warehouses.
- 35. Cont… Home Use • Consumers may be most familiar with the Roomba and other robot vacuum cleaners. However, other home robots include lawn-mowing robots and personal robot assistants that can play music, engage with children and help with household chores. Search and Rescue • Search and rescue robots can save those stuck in flood waters, deliver supplies to those stranded in remote areas and put out fires when conditions become too extreme for firefighters.
- 36. Pros and Cons of Robotics Robotics comes with a number of benefits and drawbacks. Pros of Robotics • Increased accuracy - Robots can perform movements and actions with greater precision and accuracy than humans. • Enhanced productivity - Robots can work at a faster pace than humans and don’t get tired, leading to more consistent and higher-volume production. • Improved safety - Robots can take on tasks and operate in environments unsafe for humans, protecting workers from injuries. • Rapid innovation - Many robots are equipped with sensors and cameras that collect data, so teams can quickly refine processes. • Greater cost-efficiency - Gains in productivity may make robots a more cost-efficient option for businesses compared to hiring more human workers.
- 37. Cont… Cons of Robotics • Job losses - Robotic process automation may put human employees out of work, especially those who don’t have the skills to adapt to a changing workplace. • Limited creativity - Robots may not react well to unexpected situations since they don’t have the same problem-solving skills as humans. • Data security risks - Robots can be hit with cyber attacks, potentially exposing large amounts of data if they’re connected to the Internet of Things. • Maintenance costs - Robots can be expensive to repair and maintain, and faulty equipment can lead to disruptions in production and revenue losses. • Environmental waste - Extracting raw materials to build robots and having to remove disposable parts can lead to more environmental waste and pollution.
- 38. Future of Robotics • The evolution of AI has major implications for the future of robotics. • Advanced AI also gives robots increased autonomy. • For example, drones could deliver packages to customers without any human intervention. In addition, robots could be outfitted with generative AI tools like ChatGPT, resulting in more complex human-robot conversations. • As robots’ intelligence has shifted, so too have their appearances. Humanoid robots are designed to visually appeal to humans in various settings while understanding and responding to emotions, carrying objects and navigating environments.
- 39. Cont… • With these forms and abilities, robots can become major contributors in customer service, manufacturing, logistics and healthcare, among other industries. • While the spread of robotics has stoked fears over job losses due to automation, robots could simply change the nature of human jobs. • Humans may find themselves collaborating with robots, letting their robotic counterparts handle repetitive tasks while they focus on more difficult problems. • Either way, humans will need to adapt to the presence of robots as robotics continues to progress alongside other technologies like AI and deep learning.
- 40. Chapter 8 Ethical and Legal Considerations in AI
- 41. Overview • The legal and ethical issues that confront society due to Artificial Intelligence (AI) include privacy and surveillance, bias or discrimination, and potentially the philosophical challenge is the role of human judgment. • Concerns about newer digital technologies becoming a new source of inaccuracy and data breaches have arisen as a result of its use. • AI would therefore make decisions based on informed decisions devoid of any bias and subjectivity. But there are many ethical challenges: • Lack of transparency of AI tools: AI decisions are not always intelligible to humans. • AI is not neutral: AI-based decisions are susceptible to inaccuracies, discriminatory outcomes, embedded or inserted bias. • Surveillance practices for data gathering and privacy of court users. • New concerns for fairness and risk for Human Rights and other fundamental values.
- 42. Privacy • Training of AI models requires massive amounts of data. • There is currently little insight into how the data is being collected, processed and stored which raises concerns about who can access your data and how they can use it. • There are other privacy concerns surrounding the use of AI in surveillance. Law enforcement agencies use AI to monitor and track the movements of suspects. While highly valuable, many are worried about the misuse of those capabilities in public spaces, infringing upon individual rights to privacy.
- 43. Bias • There is another ethical concern surrounding AI bias. • Although AI does not inherently come with bias, systems are trained using data from human sources and deep learning which can lead to the propagation of biases through technology. • For instance, an AI hiring tool could omit certain demographics if the data sets used to train the algorithm contained a bias against a particular group. This could also have legal implications if it leads to discriminatory practices.
- 44. Deepfakes What is deepfake AI? • Deepfake AI is a type of artificial intelligence used to create convincing images, audio and video hoaxes. • The term describes both the technology and the resulting bogus content, and is a portmanteau of deep learning and fake. • Deepfakes often transform existing source content where one person is swapped for another. They also create entirely original content where someone is represented doing or saying something they didn't do or say. • The usage of deepfakes creates ethical concerns. • Deepfakes are now able to circumvent voice and facial recognition which can be used to override security measures. The following are some specific approaches to creating deepfakes: • Source video deepfakes • Audio deepfakes • Lip syncing
- 45. AI and the future of work The Future of AI Ethics • AI ethics still has a long journey ahead, but no one truly knows where we will land when it comes to governance. • Many experts argue that ethical AI is essential for a responsible future where we can focus on issues such as social good, sustainability and inclusion. • Although the topic of AI ethics comes with a heavy dose of uncertainty, there is positive movement towards regulating this powerful technology. • Undoubtedly, Artificial Intelligence (AI) is a revolutionary field of computer science, which is ready to become the main component of various emerging technologies like big data, robotics, and IoT. • It will continue to act as a technological innovator in the coming years.
- 46. Reading Assignment Appropriate uses of AI
- 47. Thank you!! End of the Course!!