Description
In this blog post, I shall discuss on a few NLP techniques with Bangla language, demonstrate how to train a word2vec model with Bangla wiki corpus with tensor…
Summary
- Generating Text and Sentiment Analysis In this blog post, I shall discuss on a few NLP techniques with Bangla language, demonstrate how to train a word2vec model with Bangla wiki corpus with tensorflow, and explore how to visualize the semantic similarity between words using t-SNE.
- Once done, the article will focus on how to train a character / word LSTM on selected Tagore’s songs to generate songs like Tagore with keras.
- The following animation shows how the embedding is learnt to preserve the semantic similarity in the 2D-manifold more and more as training proceeds.
- Let’s first create sentiment analysis dataset by crawling the daily astrological predictions (রাশিফল) page of the online edition of আনন্দবাজার পত্রিকা (e.g., for the year 2013), a leading Bangla newspaper and then manually labeling the sentiment of each of the predictions corresponding to each moon-sign.