-
assignment 1:
Exploring word vectors (sparse or dense word representations). -
assignment 2:
Implement Word2Vec with NumPy. -
assignment 3:
Implement a neural transition-based dependency parser with PyTorch. (ref: A Fast and Accurate Dependency Parser using Neural Networks ( https://nlp.stanford.edu/pubs/emnlp2014-depparser.pdf)) -
assignment 4:
Implement neural machine translation (NMT) using a attentive encoder-decoder structure with LSTMs. (ref: Neural Machine Translation by Jointly Learning to Align and Translate (https://arxiv.org/abs/1409.0473)) -
assignment 5:
Improve NMT in assignment 4 by adding character-based encoder and decoder modules. (ref: Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models (https://arxiv.org/abs/1604.00788))