Course Description:

The general approach in the course will be covering the following:

1. A language phenomenon.
2. The corresponding language processing task.
3. Techniques based on deep learning, classical machine learning, and knowledge base.

On one hand we will understand the language processing task in detail using linguistics, cognitive science, utility etc., on the other hand we will delve deep into techniques for solving the problem. In keeping with current trends, the lectures will make heavy reference to Large Language Models. The topics are given below -

• Sound: Biology of Speech Processing; Place and Manner of Articulation; Peculiarities of Vowels and Consonants; Word Boundary Detection; Argmax based computations; Hidden Markov Model and Speech Recognition; deep neural nets for speech processing.
• Morphology: Morphology fundamentals; Isolating, Inflectional, Agglutinative morphology; Infix, Prefix and Postfix Morphemes, Morphological Diversity of Indian Languages; Morphology Paradigms; Rule Based Morphological Analysis: Finite State Machine Based Morphology; Automatic Morphology Learning; Deep Learning based morphology analysis.
• Shallow Parsing: Part of Speech (POS) Tagging; HMM based POS tagging; Maximum Entropy Models and POS; Random Fields and POS; DNN for POS.
• Parsing: Constituency and Dependency Parsing; Theories of Parsing; Scope Ambiguity and Attachment Ambiguity Resolution; Rule Based Parsing Algorithms; Probabilistic Parsing; Neural Parsing.
• Meaning: Lexical Knowledge Networks, Wordnet Theory and Indian Language Wordnets; Semantic Roles; Word Sense Disambiguation; Metaphors.
• Discourse and Pragmatics: Coreference Resolution; Cohesion and Coherence.
• Applications: Machine Translation; Sentiment and Emotion Analysis; Text Entailment; Question Answering; Code Mixing; Analytics and Social Networks, Information Retrieval and Cross Lingual Information Retrieval (IR and CLIR).