Leveraging Linguistics and Computer Science Class 11 Notes – The CBSE has updated the syllabus for St. XI (Code 843). The new notes are made based on the updated syllabus and based on the updated CBSE textbook. All the important information is taken from the Artificial Intelligence Class XI Textbook Based on the CBSE Board Pattern.
Leveraging Linguistics and Computer Science Class 11 Notes
Understanding Human Language Complexity
Linguistics is the study of language and its application in various fields like marketing, education, and AI. It focuses on the strategic application of linguistic principles and practices to meet specific objectives or goals.
NLP is a branch of Artificial Intelligence (AI) that allows computers to understand, create, and manipulate human speech. NLP has the capability to query the data with natural-language text or voice. NLP can be applied to both written text and speech.
Some examples of tools that are powered by NLP are: Web search Email spam filtering Auto-translate text or speech. Document summarization Sentiment analysis Grammar/spell checking, virtual assistants like ODA, Siri, Cortana, Alexa, etc.
Introduction to Natural Language Processing
Human language is unstructured and difficult to understand.
Let’s understand with one example, in Groucho Marx’s movie joke, “One morning I shot an elephant in my pajamas. How he got in my pajamas, I don’t know.” In the sentence, you will find that a lot of complexity is there.
The NLP algorithm helps the machine to understand human language using segmenting sentences and extracting meaning from “tokens.”. Computers begin with one sentence at a time, which is called a sentence segmentation. Computers break the sentence into small chunks of information called tokens that can be individually classified. Once the tokens in the text have been sorted into a structure based on what they mean, NLP can work with them.
Emotion Detection and Sentiment Analysis
| Aspect | Emotion Detection | Sentiment Analysis |
|---|---|---|
| Definition | Identifies distinct human emotion types. | Measures the strength of an emotion. |
| Examples | Determining if an expression is anger, happiness, etc. | Assessing if data is positive, negative, or neutral. |
| Use Cases | Analyzing user ratings, comments in surveys, etc. | Reading social media posts, customer service chats, etc. |
| AI Training | Can be trained to classify emotions. | Utilizes a sliding scale between positive and negative. |
| Purpose | Identifying emotional tokens to understand context. | Assessing the overall tone or sentiment of text data. |
Classification Problem
Here is an old-fashioned riddle:
Why does your nose run and your feet smell?
Human language is full of terms that are vague or have double meanings. This is called a classification problem.
Human language is full of ambiguity which make difficult to AI system to classified word and pharses accurately. In this riddle, the phrases “your nose run” and “your feet smell” are used in a humorous way to highlight the ambiguity of language, which poses a classification problem.
Similarly, in everyday language, phrases like “shipping a box by train” or “filling in a form by filling it out” may seem contradictory or confusing due to the double meanings of the words used. While humans can quickly grasp the intended meaning based on context, AI systems may struggle to accurately classify such phrases without a comprehensive understanding of language nuances and context.
To address this problem,
- An AI system utilizes machine learning techniques such as supervised learning.
- By feeding the system with a large dataset containing examples of language usage and their corresponding classifications, the AI system learns patterns and relationships between words, phrases, and their meanings.
- Over time and with exposure to more data, the AI system improves its classification accuracy by adjusting its internal parameters based on the observed patterns.
- AI systems may not achieve perfect classification accuracy. There will always be some degree of uncertainty or error associated with the system’s classifications.
- To address this, well-designed AI systems not only provide a response but also a confidence value, indicating the system’s level of certainty in its classification.
Chatbots
Chatbots are software applications or computer programs designed to simulate conversation with human users, typically through text-based or voice-based interactions. They use artificial intelligence (AI), natural language processing (NLP), and machine learning techniques to understand user queries and provide appropriate responses.
| Chatbots | Rule-based Chatbots | AI-powered Chatbots |
|---|---|---|
| Description | Operate on predefined rules and decision trees. Follow programmed rules to respond to user input. | Utilize natural language processing (NLP) and machine learning algorithms. Also known as chat agents or virtual assistants. |
| Advantages | – Easy to develop and maintain. – Provide consistent and accurate answers to specific questions. | – 24/7 availability for immediate and consistent support. – Offer personalized interactions based on user preferences and history. – Improve efficiency and cost savings by automating tasks and reducing service costs. |
| Limitations | – Struggle with understanding complex language. – Unable to adapt to situations beyond programmed rules. | – High development costs and resource requirements. – Prone to biases from training data and lack of transparency in decision-making. – Ethical considerations regarding privacy, manipulation, and responsible use. |
| Use Cases | – Customer service tasks like answering common questions and providing order updates. – Guiding users through specific processes. | – Entertainment and Gaming: Engage users with interactive stories and personalized gaming experiences. – Finance and Banking: Answer queries about accounts, transactions, and financial products, and process simple requests. |
Structure of a chatbot
A chatbot has a “frontend” and a “backend”.
- Frontend chatbot: The frontend of a chatbot serves as the messaging channel through which users interact, providing a user-friendly interface. However, one limitation of the frontend is that it may lack contextual understanding.
- Backend chatbot: The backend of a chatbot is where the hard work takes place. The backend operates application logic and has enough memory to remember earlier parts of a conversation as dialog continues.
Intent
An intent is a purpose: the reason why a user is contacting the chatbot. Think of it as something like a verb: a kind of action. Users may have various intents when interacting with a chatbot, such as filing a complaint, asking for directions, or speaking to a salesperson. Institutions often have multiple intents that they want their chatbots to address.
Entity
An entity is a noun: a person, place, or thing. Once you have a list of the intents you want your chatbot to fulfill, you are ready to continue. If a user asks, “What are the hours for the Bangalore office?”, then providing business hours is the intent and Bangalore is the entity.
Dialog
A dialog is a flowchart—an IF / THEN tree structure that illustrates how a machine will respond to user intents. A dialog is what the machine replies after a human asks a question. Even if a human uses run-on sentences, poor grammar, chat messaging expressions, and so on, artificial intelligence allows the NLP to understand well enough to provide a response.
Natural Language Processing – Converting Speech to Text & analysing its intent
Natural language processing (NLP) involves a series of five phases that enable machines to analyse, categorize, and understand both spoken and written language. These steps utilize deep neural network-style machine learning techniques to mimic the brain’s ability to process data accurately.
a. Lexical analysis
This step involves understanding and examining the structure of words in a language. It breaks down the text into paragraphs, phrases, and words. Lexical normalization techniques like stemming and lemmatization are commonly used to reduce words to their base forms.
- Stemming reduces words to their root form, such as removing suffixes like “ing”, “ly”, “es”, and “s”.
- Lemmatization reduces words to their dictionary form, considering factors like parts of speech (POS) to determine their meaning in context.
b. Syntactical Analysis
Syntactic Analysis is used to check grammar, word layouts, and word relationships.
Example: Mumbai travels to the Anuj.
The line “Mumbai travels to Anuj” makes no sense, hence it is rejected by the Syntactic Analyzer. Syntactical parsing is the analysis of words in a sentence for grammar. Dependency Grammar and Part of Speech (POS) tags are significant syntactic elements.
c. Semantic Analysis
Semantic analysis aims to understand the various meanings conveyed by a sentence in a clear and contextually appropriate manner. It extracts relevant insights from the text to comprehend its intended message.
d. Discourse Integration
This involves understanding the context of a statement or word based on preceding sentences or words. It helps interpret references like pronouns and proper nouns by identifying their connections with earlier parts of the conversation.
Example – Arti wants it.
We can observe from the following sentence that the “it” keyword makes no sense. In reality, it applies to anything we don’t know. That is all this “it” word depends on the prior sentence, which is not provided. So, if we know what “it” is, we can simply find the reference.
e. Pragmatic Analysis
It denotes the study of meanings in a particular language. Process of extracting insights from a text. It involves verbal repetition, such as “who said what to whom?” It recognizes how individuals communicate with one another, the context in which they are speaking, and many other factors.
Applications of NLP
Sentiment analysis: Sentiment analysis is a natural language processing technique that judge the emotion and the intent of the text. Sentiment analysis classifies text as positive, negative, or neutral. This technique is used for customer satisfaction and is used in business and in social media.
Voice assistants: Natural language processing is used in voice assistants like Google Assistant, Siri, and Alexa. NLP helps to understand the spoken commands from the users, process the language, and provide some meaningful response. For example:
- Hey Google, set an alarm at 3.30 pm
- Hey Alexa, play some music
- Hey Siri, what’s the weather today.
Email Filtering: Email is a part of our daily lives. We find ourselves bombarded with emails about job, study, and a variety of other topics. We receive emails from a variety of sources; some are work-related or from our dream school or institution, while others are spam or promotional in nature. Here, Natural Language Processing comes into play. It classifies incoming emails as “important” or “spam” and assigns them accordingly.
Document Analysis: Document analysis is another use of natural language processing. Companies, institutions, and schools, among other places, are constantly inundated with data that must be properly organized, stored, and searched. All of this may be accomplished with NLP. It not only searches a keyword but also categorizes it according to the instructions, saving us from the tedious and time-consuming task of searching for a single person’s information from a large number of files.
Automatic Summarization: Data has grown in line with technological advancements. This rise of data has broadened the scope of data processing. Still, manual data processing is time-consuming and error-prone. NLP provides a solution for this as well; it can not only summarize the meaning of information but also identify the emotional meaning hiding within it.
Disclaimer: We have taken an effort to provide you with the accurate handout of “Leveraging Linguistics and Computer Science Class 11 Notes“. If you feel that there is any error or mistake, please contact me at anuraganand2017@gmail.com. The above CBSE study material present on our websites is for education purpose, not our copyrights. All the above content and Screenshot are taken from Artificial Intelligence Class 11 CBSE Textbook and Support Material which is present in CBSEACADEMIC website, This Textbook and Support Material are legally copyright by Central Board of Secondary Education. We are only providing a medium and helping the students to improve the performances in the examination.
Images shown above are the property of individual organizations and are used here for reference purposes only.
For more information, refer to the official CBSE textbooks available at cbseacademic.nic.in