Assignments and Supplemental Reading Materials

Now that you have built a project and completed the quiz, you are ready to move on to the next step: exploring supplemental reading materials and completing the provided assignments to better understand the topics we discussed.

Supporting reading materials

1. GloVe: Global Vectors for Word Representation by Jeffrey Pennington, Richard Socher, and Christopher D. Manning. This is the original paper that introduced the GloVe embeddings. If you skip this paper, then you are skipping some of the most important and interesting techniques that are used to create word vectors. Also, you must read this because, in the latter part of the course, we are going to use GloVe embedding to create our project.

2. Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis by Seyed Mahdi Rezaeinia et al. This paper proposes a novel method, Improved Word Vectors (IWV), which increases the accuracy of pre-trained word embeddings in sentiment analysis. Their method is based on Part-of-Speech (POS) tagging techniques, lexicon-based approaches, and word2vec/GloVe methods. This is a must-read paper and is also written in an easy-to-read manner.

3. Comparative study of word embedding methods in topic segmentation by Marwa Naili et al. in 2017. This paper discusses three types of word embedding in the context of topic segmentation. This paper also provides different models and approximation algorithms for word2vec embedding.