Scribd
Upload
11 views6 pages

NLP 2 Chapter 2

Chapter 2 discusses morphology analysis, focusing on the structure and formation of words through morphemes, including free and bound morphemes. It covers inflectional and derivational morphology, highlighting their roles in grammatical categories and word creation, as well as techniques like stemming and lemmatization for text processing. Additionally, it introduces regular expressions for defining search patterns in text.

Uploaded by

jaloj24591
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
11 views6 pages

NLP 2 Chapter 2

Chapter 2 discusses morphology analysis, focusing on the structure and formation of words through morphemes, including free and bound morphemes. It covers inflectional and derivational morphology, highlighting their roles in grammatical categories and word creation, as well as techniques like stemming and lemmatization for text processing. Additionally, it introduces regular expressions for defining search patterns in text.

Uploaded by

jaloj24591
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Word Level

Analysis
CHAPTER 2
 1. Morphology Analysis
 Morphology is the study of the structure and formation of words in a language.
 Definition: Morphology analyzes how words are formed by combining morphemes
(smallest meaningful units).
 Types of Morphemes:
 Free morphemes: Stand alone as words (e.g., "book").
 Bound morphemes: Cannot stand alone (e.g., "-ed" in "played").
 Importance in NLP: Morphology aids in text analysis tasks like tokenization, parsing, and
information retrieval.
 Inflectional Morphology: Modifies a word to express tense, mood, number, etc. (e.g.,
"run" → "running").
 Derivational Morphology: Creates new words with new meanings by adding prefixes or
suffixes (e.g., "happy" → "unhappy").
•Morphological Parsing: Decomposes words into their root forms and affixes.

•Challenges: Handling irregular forms (e.g., "go" → "went") and language-specific variations.

•Applications: Used in machine translation, spell-checking, and text normalization.

•Tools: Morfessor, NLTK Morphological Analyzer, SpaCy Morphology.

•Cross-Linguistic Morphology: Languages like Finnish and Turkish are morphologically rich, making
analysis more complex.
 2. Inflectional Morphology & Derivational Morphology
 Inflectional Morphology
 Definition: Focuses on modifying a word’s form to indicate grammatical categories (e.g.,
"cat" → "cats").
 Grammatical Categories: Includes tense, number, case, gender, aspect, and mood.
 Limited Effect: Does not change the core meaning or word class (e.g., "walk" →
"walked").
 Examples in English: Plural forms ("dogs"), past tense ("played"), comparative
("smarter").
 Regular vs. Irregular Inflection: Regular patterns follow rules (e.g., add "-ed"), while
irregular forms do not (e.g., "sing" → "sang").
 Applications: Used in POS tagging, grammar correction, and dependency parsing.
 Cross-Language Examples: German uses suffixes for case and gender (e.g., "Hund" →
"Hunde").
 Role in Sentence Construction: Essential for subject-verb agreement in languages
with rich inflection.
 Simpler in English: English has fewer inflectional markers compared to languages like
Russian or Arabic.
 NLP Impact: Helps understand morphological variance in syntactic analysis.
 Derivational Morphology
 Definition: Involves creating new words by adding prefixes, suffixes, or other affixes.
 Examples: Adding "-ness" to "happy" to form "happiness" or "un-" to "do" to form "undo."
 Word Class Changes: Often changes the grammatical category (e.g., noun → adjective).
 Prefix and Suffix: Prefixes like "pre-" and "re-" often indicate time, while suffixes like "-
ation" indicate actions.
 Recursive Derivation: Multiple derivational processes can apply to the same word (e.g.,
"modernize" → "modernization").
 Meaning Changes: Derivation often creates significant semantic shifts (e.g., "clear" →
"clarify").
 Language-Specific Rules: Different languages have unique derivational affixes.
 Applications: Used in text generation, translation, and language learning tools.
 Complexity: Derivational processes can involve compounding and blending (e.g.,
"brunch").
 NLP Challenges: Requires understanding context to ensure correct derivation.
 3. Stemming and Lemmatization
 Definition: Techniques to reduce words to their base forms for text processing.
 Stemming:
 Removes affixes to produce the stem.
 Often results in non-standard words (e.g., "studying" → "studi").
 Algorithm: Porter Stemmer, Snowball Stemmer.
 Lemmatization:
 Reduces words to their dictionary form (lemma).
 Considers context and part of speech (e.g., "better" → "good").
 Applications: Search engines, information retrieval, and text normalization.
 Comparison: Lemmatization is more accurate but computationally intensive
compared to stemming.
 Example:
 Stemming: "flies" → "fli"
 Lemmatization: "flies" → "fly."
 Role in NLP Pipelines: Often used during preprocessing for feature extraction.
 Challenges: Handling polysemous words (e.g., "bank" as a verb vs. noun).
 Multilingual Support: Tools like SpaCy provide language-specific lemmatizers.
 Future Trends: Integration with deep learning for better contextual understanding.
 Regular expression :
 A regular expression (regex) is a sequence of characters that
define a search pattern. Here’s how to write regular expressions:
 Start by understanding the special characters used in regex, such
as “.”, “*”, “+”, “?”, and more.
 Choose a programming language or tool that supports regex,
such as Python, Perl, or grep.
 Write your pattern using the special characters and literal
characters.
 Use the appropriate function or method to search for the pattern
in a string.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy