1.

Write a Short note on NLP: Natural Language Processing (NLP) is an interdisciplinary

field that combines computer science, artificial intelligence, and linguistics to enable
computers to understand, interpret, and generate human language in a way that is both
meaningful and useful. The ultimate goal of NLP is to bridge the gap between human
communication and computer understanding. This involves developing algorithms and
statistical models that can process and analyze large amounts of natural language data. NLP
applications are vast and include machine translation, sentiment analysis, speech
recognition, text summarization, and more. It plays a crucial role in enhancing user
experience in search engines, social media, customer service chatbots, and personal
assistants like Siri and Alexa.
2. Difference between Syntactic ambiguity and Lexical ambiguity:
 Lexical Ambiguity: This occurs when a word has multiple meanings, leading to
different interpretations of a sentence. For example, the word "bank" can refer to a
financial institution or the side of a river. The context in which the word is used is
crucial for determining its meaning.
 Syntactic Ambiguity: This type of ambiguity arises when a sentence can be parsed
in different ways, leading to different interpretations. For instance, the sentence "The
man saw the girl with the telescope" can be ambiguous because it's unclear whether
the man used a telescope to see the girl or if the girl had a telescope.
3. Different Stages in NLP Step by Step with Suitable Example:
 Tokenization: This is the process of breaking down text into individual units
(tokens), such as words or phrases. For example, the sentence "Hello, world!" would
be tokenized into ["Hello", ",", "world", "!"].
 Part-of-Speech Tagging: Here, each token is assigned a grammatical category, like
noun or verb. For example, "The cat sat" would be tagged as [Determiner, Noun,
Verb].
 Parsing: This involves analyzing the grammatical structure of sentences to
understand the relationships between words. It helps in identifying the sentence
structure.
 Semantic Analysis: This stage involves understanding the meaning of sentences. It
might involve named entity recognition (identifying proper nouns) or sentiment
analysis (determining the sentiment expressed in the text).
 Disambiguation: This is the process of resolving ambiguities in language, which
could be lexical or syntactic. For example, in the sentence "I went to the bank to
deposit my check," the word "bank" could be disambiguated based on the context.
2. Challenges in NLP / Application of NLP:
 Challenges: Handling ambiguity, understanding context, dealing with slang and new
words, processing large volumes of data, and understanding complex human
emotions and sarcasm are some of the challenges in NLP.
 Applications: NLP is used in various applications such as chatbots, search engines,
language translation services, content recommendation systems, and more. It
enhances user experience by making interactions with technology more natural and
intuitive.
2. Advantages and Disadvantages of NLP:
 Advantages: Improved communication between humans and machines, automation
of manual tasks, enhanced data analysis capabilities, and personalized user
experiences.
 Disadvantages: Privacy concerns, challenges in understanding complex human
emotions and sarcasm, potential for misinterpretation of data, and the need for large
amounts of training data.
2. Explain the ambiguity associated at each level with example for NLP:
 Lexical Ambiguity: As mentioned, a word can have multiple meanings. For
example, "bank" could refer to a financial institution or the side of a river.
 Syntactic Ambiguity: As mentioned, the sentence "The man saw the girl with the
telescope" can be ambiguous because it's unclear whether the man used a telescope
to see the girl or if the girl had a telescope.
 Semantic Ambiguity: This involves ambiguity in the meaning of the words. For
example, "The car hit the pole while it was moving" can be ambiguous because it's
unclear whether the car or the pole was moving.
 Anaphora Ambiguity: This arises due to the use of anaphORA entities in discourse.
For example, "The horse ran up the hill. It was very steep. It soon got tired." Here,
"it" could refer to the hill or the horse.
 Pragmatic Ambiguity: This refers to the situation where the context of a phrase
gives it multiple interpretations. For example, the sentence "I like you too" can have
multiple interpretations like "I like you (just like you like me)" or "I like you (just
like someone else does)".
2. Tokenization / Need of Tokenization / Benefits of Tokenization / Challenges in
Tokenization:
 Tokenization: It is the process of breaking down text into individual units (tokens),
such as words or phrases.
 Need: It is needed to convert text into a format that can be processed by NLP
algorithms.
 Benefits: It includes easier parsing, part-of-speech tagging, and feature extraction.
 Challenges: Dealing with punctuation, special characters, and context-dependent
tokenization.
2. Difference between Lemmatization and Stemming:
 Lemmatization: It considers the context and correctly identifies the base form of a
word (lemma). For example, it would turn "running" into "run".
 Stemming: It simply chops off the end of the word, which might not always result in
a valid word. For example, it might turn "running" into "runn".
2. What is morphology and Different types of Morphology:
 Morphology: It is the study of the structure and formation of words in a language.
 Types:
 Inflectional Morphology: Changes in word form to express grammatical
functions, like tense, case, or number.
 Derivational Morphology: Changes in word form to create new words with
different meanings, like "happy" to "happiness" or "unhappy".
 Compounding: Forming new words by combining two or more existing
words, like "bookstore" or "newspaper".