Natural Language Processing with Deep Learning (CAI401) introduces students to the fundamental concepts, techniques, and computational approaches used to process and understand human language. The course covers linguistic aspects of morphology, syntax, semantics, discourse, and pragmatics, along with statistical and machine-learning approaches to NLP. CSP405
Students begin with NLP foundations, including regular expressions, automata, morphology, finite-state transducers, N-gram language models, smoothing techniques, entropy, Hidden Markov Models, and the Viterbi algorithm. The course then progresses to syntax, part-of-speech tagging, parsing, word-sense disambiguation, and machine translation.
The course also introduces practical text and language processing, including text corpora, lexical resources such as WordNet, regular expressions, text normalization, tokenization, segmentation, and statistical analysis of text.
Further topics include text classification, tagging, information extraction, chunking, Named Entity Recognition, and relation extraction, followed by advanced linguistic analysis involving context-free grammars, dependency grammar, feature-based grammar, sentence semantics, discourse semantics, and linguistic data management.
In short
The course aims to enable students to:
- Understand the linguistic and computational foundations of NLP
- Apply statistical and machine-learning techniques to language processing
- Perform tasks such as tokenization, POS tagging, parsing, WSD, classification, NER, and information extraction
- Work with corpora, lexical resources, and NLP software libraries
- Develop NLP systems of moderate complexity
- Evaluate NLP systems and perform error analysis
Students begin with NLP foundations, including regular expressions, automata, morphology, finite-state transducers, N-gram language models, smoothing techniques, entropy, Hidden Markov Models, and the Viterbi algorithm. The course then progresses to syntax, part-of-speech tagging, parsing, word-sense disambiguation, and machine translation.
The course also introduces practical text and language processing, including text corpora, lexical resources such as WordNet, regular expressions, text normalization, tokenization, segmentation, and statistical analysis of text.
Further topics include text classification, tagging, information extraction, chunking, Named Entity Recognition, and relation extraction, followed by advanced linguistic analysis involving context-free grammars, dependency grammar, feature-based grammar, sentence semantics, discourse semantics, and linguistic data management.
In short
The course aims to enable students to:
- Understand the linguistic and computational foundations of NLP
- Apply statistical and machine-learning techniques to language processing
- Perform tasks such as tokenization, POS tagging, parsing, WSD, classification, NER, and information extraction
- Work with corpora, lexical resources, and NLP software libraries
- Develop NLP systems of moderate complexity
- Evaluate NLP systems and perform error analysis
- Teacher: Sanjeev Kumar Sharma
- Teacher: Shikha Magotra