Overview
Explore text classification and sequence labeling in multilingual natural language processing through this comprehensive lecture from CMU's CS11-737 course. Delve into various models, techniques, and datasets used for these tasks, including neural networks, recurrent neural networks, and feedforward neural networks. Learn about language identification, named entity recognition, and composite benchmarks. Gain insights into the application of these concepts in multilingual contexts, with a focus on practical implementation and real-world datasets. Enhance your understanding of NLP fundamentals and advanced techniques for processing text across multiple languages.
Syllabus
Introduction
Text Classification
Sequence labeling
Span labeling
Text segmentation
extractor
predictor
classification
alternative methods
what are neural networks
computation graphs
Graph construction
Backpropagation
Neural Network Framework
Recurrent Neural Networks
FeedForward Neural Networks
featurizing a sequence
rnns
rnn
Summary
Multilingual Labeling
Language Identification
Text Classification Data Sets
Sequence Labeling Data Sets
Named Entity Recognition Data Sets
Composite Benchmarks
Class Discussion
Taught by
Graham Neubig