|
|
|
|
|
linguist.page@gmail.com
Home
»
Computational Linguistics
»
Linguistics Knowledge (Formalized for CL)
Phonetics & Phonology (Computational)
(5)
Phoneme representation
International Phonetic Alphabet (IPA) encoding
Feature matrices
Speech sounds as signals
Acoustic phonetics basics (for speech processing)
Morphology (Computational)
(8)
Morphemes, affixes, roots
Inflection vs. derivation
Finite-State Morphology
Morphological analyzers
Stemming vs. Lemmatization
Tokenization (word, subword, character)
Byte-Pair Encoding (BPE)
WordPiece & Unigram tokenization
Syntax (Computational)
(8)
Phrase structure grammars (CFG, PCFG)
Chomsky Normal Form (CNF)
Dependency grammars
Constituency parsing
Dependency parsing
Treebanks (Penn Treebank, Universal Dependencies)
Parse trees as data structures
Ambiguity and probabilistic parsing
Semantics (Computational)
(12)
Word meaning representation
Lexical semantics (synonymy, polysemy, hypernymy)
WordNet & ontologies
Distributional semantics
Vector space models
Word embeddings (Word2Vec, GloVe, FastText)
Contextual embeddings
Compositional semantics
Formal semantics (lambda calculus basics)
Semantic role labeling
Frame semantics (FrameNet)
Abstract Meaning Representation (AMR)
Pragmatics & Discourse (Computational)
(7)
Coreference resolution
Anaphora resolution
Discourse structure
Rhetorical Structure Theory (RST)
Coherence & cohesion
Dialogue acts
Speech acts
Typology & Multilingual NLP
(6)
Language families & their computational implications
Agglutinative vs. fusional vs. isolating
Low-resource languages
Cross-lingual transfer
Multilingual models (mBERT, XLM-R)
Code-switching