Dhivehi to English translation with Microsoft translator

The Dhivehi language translation feature included in Microsoft translator and Microsoft 365 lets you press a button and translate written Dhivehi into English. Though there are a few hiccups here and there, the service is great and provides an understanding of the overall document. This is more than what we see from any existing models.

I was amazed to see a link in one of my outlook web emails, it says “translate message to: English” which could mean nothing usually, however, when I saw the next sentence which said “Never translate from: Divehi”, I thought why would it says Divehi specifically if it doesn’t understand that the entire email was written in Dhivehi? Out of curiosity, I pressed the button, and to my surprise, it was quite good. The essence of the message was retained very well.

For example, something like އިޙްތިރާމް ޤަބޫލުކުރެއްވުން އެދެން could be translated as “I would like to respect you”, which is ok in terms of translation, but what it meant was greetings to you.

Nevertheless, I feel this is great progress. Microsoft says that translator is part of Microsoft cognitive services, and now I am very curious to check out how we could leverage the cognitive services to Dhivehi language-specific tasks without training a Dhivehi language model from scratch. To me, this means a world of possibilities opening up for us.

There are several NLP models and many great language services, especially I salute the people at Dhivehi.ai for their text to speed model and working on a Speech to text model, It seems the benefit of AI has now started to touch our lives in ways we did not foresee for a language like Dhivehi.

Comments

The Role of Research in Progress and Innovation

The history of human progress is a testament to the impact of research for the sake of research. Visionaries like Galileo, Isaac Newton, and Albert Einstein have expanded our understanding of the universe by fearlessly pursuing knowledge and sharing their discoveries through academic publications. The scientific method, which promotes the validation of any claim through verification, is a cornerstone of the research process and has driven transformative innovations. Consider the rise of smart cities, which integrate cutting-edge technologies to enhance urban life. Between 2018 and 2021, Singapore produced more than 1,500 research papers on smart cities, while Amsterdam published more than 950 such papers. These contributions demonstrate the critical role research plays in realizing the potential of smart city initiatives. Where ever, there was an attempt to redefine the norm, it was the 'research' that made that happen. Bitcoin, a revolutionary digital currency, emerged from ...

How the "push it" culture creates real "down fall".

In the world of organizational culture, the prevalence of a "push it" mentality often serves as a glaring indicator of more profound issues. It signifies more than just a commitment to excellence; it frequently represents the single most significant indication of an isolated, blame-oriented, and ultimately toxic culture. In environments where the "push it" mantra prevails, collaboration becomes an afterthought, and leaders, whether consciously or inadvertently, exacerbate this toxicity by embracing this phrase. In this article, I will dive into the perils of the "push it" culture, and I will try to shed some light. If you have been hearing the phrase "you have to push it" or "I expect you to push it harder", that means you are already working in a counterproductive environment. The Toxicity of "Push It" The "push it" culture, seemingly rooted in the pursuit of results, often conceals deeper organizational maladies....

Google dialogflow - How to train a chatbot to answer questions related to your office and how to make it better than just a Q&A bot?

First lets look how to do it the basic way. To train a conversational AI chatbot for answering office-related queries using Dialogflow, you will need to follow these steps: Create a new agent in Dialogflow. Collect a dataset of office-related queries and their corresponding answers. This dataset can be obtained through various means, such as scraping websites, conducting surveys, or manually creating a dataset. Create intents in Dialogflow for the queries in your dataset. An intent represents a user's intention, such as asking for office hours or requesting a vacation day. Add training phrases to each intent, which are examples of how a user might ask the question. Provide responses for each intent, which will be the chatbot's answer to the user's query. Test the chatbot using the "Try it now" feature in Dialogflow. Once the chatbot is working well, you can deploy it to a platform of your choice, such as a website or mobile app. However, if you follow the basic ...

Windhu - "Pulse"

Search This Blog