MILES VS rasa

MILES is a multilingual text simplifier inspired by LSBert — A BERT-based lexical simplification approach proposed in 2018. Unlike LSBert, MILES uses the bert-base-multilingual-uncased model, as well as simple language-agnostic approaches to complex word identification (CWI) and candidate ranking. Although not all have been tested, MILES should support 22 languages: Arabic, Bulgarian, Catalan, Czech, Danish, Dutch, English, Finnish, French, German, Hungarian, Indonesian, Italian, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swedish, Turkish, and Ukrainian.

Recently, I started working on another simplifier called MILES. MILES is loosely inspired by LSBert — another lexical simplifier that uses the large BERT uncased model to find substitutions for complex words. MILES works in a very similar way, however, it instead makes use of the multilingual BERT model, as well as fully language-agnostic methods for complex word identification and substitution ranking. As a result, MILES can (in theory) support a multitude of different languages. The GitHub repository can be found here, and below I've included an example text simplified by MILES, as well as an overview of the framework.

Support Rasa on GitHub ⭐

It itself is not a GPT. It is a a framework of a framework project built on top of Rasa (https://github.com/RasaHQ/rasa) and Langchain which by default uses gpt3.5-turbo (change it in the .env file) or any foundation model you wish.

There was already a GitHub issue https://github.com/RasaHQ/rasa/issues/11084 but it seems like there was no solution provided.

Rasa - also an open source platform. You can use it to build chatbots that are more in line with customer service and sales. Reading that, it’s kind of a big yikes for people under this kind of job knowing you can automate a part of their job via a chatbot. I think they also have a Pro version which is an extension that has additional analytics and probably more security features. I probably will check out the Open source one first and maybe ask about what the Pro version is.

At the moment it can recognise the type of statements in the training data set [1] and transpile them to Python, Java or C++ using the mappings defined here [2].

This is very different from how Codex/Autopilot work as it is trained using an NLU framework [3] which is usually used for training chatbots.

[1]: https://github.com/Flex-lang/transpiler/tree/master/transpil...

[2]: https://github.com/Flex-lang/transpiler/tree/master/transpil...

[3]: https://github.com/RasaHQ/rasa

Check out Rasa

It looks like it is built upon a Chatbot platform called “messengerx.io”, which itself seems to be built upon an open-source/machine-learning framework for voice/text conversations called “Rasa”

Use Python and use the Rasa framework to make a chat bot. https://rasa.com/docs/

This example is sourced from RasaHQ