Ce diaporama a bien été signalé.
Le téléchargement de votre SlideShare est en cours. ×

Poem Generator.pptx

Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Prochain SlideShare
Untitled presentation.pptx
Untitled presentation.pptx
Chargement dans…3
×

Consultez-les par la suite

1 sur 13 Publicité
Publicité

Plus De Contenu Connexe

Plus récents (20)

Publicité

Poem Generator.pptx

  1. 1. Poem Generator NLP project Aditya Mahakali [21/10/JC/026] Rahul Das [21/10/JC/018]
  2. 2. Overview of what we have done? 1. Scraped poems of various authors from https://mypoeticside.com/poets/ 2. Preprocessed those poems, cleaned them and created a dataframe of all the lines. 3. Using spacy(open-source NLP library) and lstm(RNN) we have generated poems from a theme given by user. 4. Using flask to create a basic web-app as frontend.
  3. 3. Poets emulated 1) William-Shakespeare 2) JokeR-D-Toxic (a.k.a. Rahul Das) 3) Rabindranath-Tagore 4) Emily-Dickinson 5) Sarojini-Naidu 6) Robert-Frost 7) William-Wordsworth
  4. 4. Scraping using bs4
  5. 5. preprocessing Converted poems into a corpus of verses for each poet to conserve vocabulary and writing style.
  6. 6. Poem Generation Using Spacy To find similarity between our theme word and poems we use a large corpus of words included in spacy. “en_core_web_lg”
  7. 7. Generation Algorithm Select a initial word First we randomly select n verses Then we choose the verse with highest similarity to initial word Compute similarity between initial words and all n verses Set initial word to that verse
  8. 8. GUI (web-app) using flask
  9. 9. GUI (web-app) using flask
  10. 10. Poem Generation Using LSTM(tried) LSTM (Long Short-Term Memory) network is a type of RNN (Recurrent Neural Network) that is widely used for learning sequential data prediction problems. As every other neural network LSTM also has some layers which help it to learn and recognize the pattern for better performance.

×