Sinhala Search Engine - Sri Lankan Actors/Actresses

Sri Lankan Actors/Actresses search engine using Sinhala language. The search engine presents following functions.

• Search acted movies by actor/actress - දමිතා අබේරත්න රංගනය කල නාට්ය
• Search bio by actor/actress name - දමිතා අබේරත්නගේ විස්තර
• Search career info by actor/actress name - දමිතා අබේරත්නගේ වෘත්තීය දිවිය
• Search awards by player name - දමිතා අබේරත්නගේ සම්මාන
• Search actresses by movies - මීහරකා චිත්රපටයේ නිළියන්
• Search actresses by awards - හොඳම නිළිය සම්මානය ලබාගත් නිළියන්
• Search actors by awards - හොඳම නළුවා සම්මානය ලබාගත් නළුවන්
• Search actors by movies - සඳ මඩල චිත්රපටයේ නළුවන්
• Search actors/actress by movies - සඳ මඩල චිත්රපටයේ නළුනිළියන්

Quickstart

• Start an ElasticSearch Instance on the port 9200
• Run data_upload.py file to create index
• Run command flask run to start the application
• App will start on http://127.0.0.1:5000/
• Visit http://127.0.0.1:5000/ and search by entering relevant queries in Sinhala language

Directory Structure

• /corpus - Contains the scrapped actor data set
• /templates - Contains the User interface templates
• web_scraper.py - Contains the code used to scrape the web
• data_upload.py - Contains code to create the index
• preprocessor.py - Contains the logic of the search engine
• app.py - Contains the code to run flask server

Corpus

Actor/Actress data along with the metadata was scraped from Wikipedia. The corpus consists of following data fields for each actor/actress.

• Name - Name of the Actor/ Actress
• Career - Career information
• Bio - Personal life or biography
• Films - Acted films
• Awards - Received awards
• Dob - Date of birth
• Gender - Gender of the person
• Active_years - Years which he or she acted
• Vital_status - Vital status of the person

Name, Career, Bio, Films and Awards were translated to Sinhala

Additional Features

• Intent Classification - Query intention is found by intent classification
• Query Preprocessing - According to the intent queries are pre processed
• Synonyms support for certain words related to cinema industry - වෘත්තීය දිවිය, සිනමා ජීවිතය
• Simple spelling errors are supported - නිළියන්, නිලියන්