|
|
|
|
|
linguist.page@gmail.com
Home
»
Computational Linguistics
»
Core NLP Tasks & Methods
Text Preprocessing
(6)
Sentence segmentation
Tokenization
Normalization (lowercasing, punctuation)
Stop word removal
Spelling correction
Text cleaning
Text Representation
(6)
Bag of Words (BoW)
TF-IDF
N-gram models
Word embeddings
Sentence embeddings
Document embeddings
Language Modeling
(6)
N-gram language models
Smoothing techniques
Neural language models
Autoregressive language modeling
Masked language modeling
Perplexity as evaluation
Sequence Labeling
(8)
Part-of-Speech (POS) tagging
Named Entity Recognition (NER)
Chunking
Slot filling
BIO/IOB2 tagging scheme
HMM-based taggers
CRF-based taggers
Neural taggers
Parsing
(4)
Constituency parsing
Dependency parsing
Semantic parsing
Grammar induction
Classification Tasks
(5)
Text classification
Sentiment analysis
Topic classification
Authorship identification
Language identification
Sequence-to-Sequence Tasks
(5)
Machine Translation (MT)
Text summarization
Paraphrase generation
Text simplification
Grammatical Error Correction
Information Extraction
(5)
Named Entity Recognition (NER)
Relation extraction
Event extraction
Open Information Extraction (OpenIE)
Template filling
Question Answering
(5)
Extractive QA (SQuAD-style)
Abstractive QA
Open-domain QA
Closed-book QA
Reading comprehension
Dialogue & Conversational AI
(7)
Task-oriented dialogue
Open-domain dialogue
Intent detection
Slot filling
Dialogue state tracking
Response generation
Retrieval-augmented generation
Lexical & Semantic Tasks
(5)
Word sense disambiguation (WSD)
Semantic textual similarity
Textual entailment / Natural Language Inference (NLI)
Semantic role labeling (SRL)
Coreference resolution
Speech & Audio (Spoken Language Processing)
(7)
Waveforms & sampling
Fourier Transform & spectrograms
Mel-frequency cepstral coefficients (MFCCs)
Automatic Speech Recognition (ASR)
Text-to-Speech (TTS)
Speaker diarization
Prosody modeling