| 1 |
To implement text preprocessing techniques such as tokenization, case folding, stemming, lemmatization, and calculate the edit distance between text strings. |
| 2 |
Create unigram, bigram, and trigram language models. Apply smoothing techniques to handle unseen data. Compute the perplexity of a given test sentence. |
| 3 |
To construct a Part-of-Speech (POS) tagger using the Hidden Markov Model (HMM) and implement the Viterbi algorithm to decode the most probable sequence of tags for a given sentence. |
| 4 |
Implement Recurrent Neural Network (RNN) architectures for next-word prediction using pre-trained word embeddings such as Word2Vec or GloVe. |
| 5 |
Construct Context-Free Grammars (CFGs) to generate sentences applying top-down and bottom-up parsing algorithms for syntactic analysis. |
| 6 |
To implement Probabilistic Context-Free Grammars (PCFGs) for statistical parsing and explore dependency parsing using graph-based and transition-based methods for syntactic analysis. |
| 7 |
Implement and compare two approaches to Word Sense Disambiguation (WSD): Supervised Approach: Using a Decision Tree classifier for WSD and Unsupervised Approach: Using the Lesk Algorithm for WSD. |
| 8 |
To implement Information Extraction using Named Entity Recognition (NER) and Relation Extraction. |
| 9 |
Construct Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) Systems using Deep Learning Techniques. |
| 10 |
Build a Neural Machine Translation model using sequence-to-sequence (Seq2Seq) architecture with attention mechanisms. |