Skip to main content

Tutorials

Train and deploy NLU applications through the following Google Colab/GitHub tutorials by NeuralSpace.

- Hate Police Twitter Bot:​

 Open In GitHub

  • Social media sites, being user-friendly and a free source, provide opportunities for people to air their voices. People, irrespective of age group, use these sites to share every moment of their lives, making these sites flooded with data. Due to the lack of restrictions set by these sites for their users to express their views as they like, anyone can make adverse and unrealistic comments in abusive language against anybody with an ulterior motive to tarnish one’s image and status in society.

  • Furthermore, the contents on such social media are spread in so many different languages. It becomes a huge responsibility for these sites to identify such hate content before it disseminates to the masses.

  • Let us use NeuralSpace's Language Understanding to build an end-to-end Twitter bot which classfies hate and offensive tweets in English, Hindi and Marathi languages.

Data License ✅

For this tutorial, NeuralSpace has utilised corresponding training and testing data of the HASOC 2021 (Hate Speech and Offensive Content Identification in English and Indo-Aryan Language) International Competition organised from 25th July 2021 to 30th July 2021.

- Citizen Service:​

 Open In GitHub

  • Citizen services refer to the essential services provided by organizations to general citizens. In this case, we focus on important services like First Information Report (FIR), Blood/Platelets Donation, and Coronavirus-related queries etc.

  • Despite the importance of citizen services, linguistically rich countries like India are still far behind in delivering such essential needs to its citizens with ease. The best services currently available do not exist in various low-resource languages that are native to different groups of people. This challenge aims to make government services more efficient, responsive, and citizen-friendly.

  • As our computing resources and modeling capabilities grow, so does our potential to support our citizens by delivering a far superior experience to them. Equipping a citizen services bot with the ability to converse in vernacular languages would make them accessible to a vast group of people for whom English is not a language of choice, but who are increasingly turning to digital platforms and interfaces for a wide range of needs and wants.

  • Let us NeuralSpace's Language Understanding to build a Citizen service NLU engine in eight languages namely, English, Hindi, Bengali, Punjabi, Tamil, Telugu, Gujarati and Marathi.

Data License ✅

For this tutorial, NeuralSpace has built this dataset in-house. All rights related to this dataset belong to NeuralSpace. If you would like to use this dataset for other purposes than this tutorial, please contact us at hello@neuralspace.ai.

- E-commerce Service:​

 Open In GitHub

  • As our computing resources and modeling capabilities grow, so does our potential to support our citizens by delivering a far superior customer experience. Equipping an e-commerce services bot with the ability to converse in vernacular languages would make them accessible to a vast group of people for whom English is not a language of choice, but who are increasingly turning to digital platforms and interfaces for a wide range of needs and wants.

  • Let us NeuralSpace's Language Understanding to build a multilingual E-Commerce service NLU.

Data License ✅

For this tutorial, NeuralSpace has built this dataset in-house. All rights related to this dataset belong to NeuralSpace. If you would like to use this dataset for other purposes than this tutorial, please contact us at hello@neuralspace.ai.