We'll use the "natural" NLP library; follow the previous session to understand how to set up your environment. - Source: dev.to / almost 2 years ago

Several NLP libraries are available, each offering distinct features and functionalities. One popular choice in the JavaScript ecosystem is the Natural Language Toolkit for JavaScript (NLP.js), which provides a wide range of NLP capabilities. - Source: dev.to / almost 2 years ago

For a JS based approach you could try NLP libraries like this one: https://github.com/axa-group/nlp.js. Source: about 2 years ago

To determine which chatbot intent is the best match for the user textual input, we rely on nlp.js (in JS) though we are in the process of moving to our new Python NLP server for better optimization of the needs of eCommerce conversations. A preprocessor language model is also used to improve the chances of a matching. - Source: dev.to / almost 3 years ago

Probably not. In fact, in Xatkit we aim to be a chatbot orchestration platform exactly to avoid reinventing the wheel and the non-invented here syndrome. So, in most cases, other existing platform (like DialogFlow or nlp.js) will work just fine. But we have also realized that there are always some particularly tricky bots for which you really need to be able to customize your engine to the specific chatbot... - Source: dev.to / about 3 years ago

Here is one library that will be used for the training https://fasttext.cc/ this allows for the consensus across multiple languages so that we can define our mystery word correctly. Source: over 3 years ago

(response to edit) > The classification problem is interesting though. I ended up with a long list of hundreds of topics. Most articles fall in two or more. There's also a sub-problem of clustering news by subject. Yeah, certainly difficult. I'm doing it partially manually right now but also with fastText[1]. I'd like to switch completely to fastText soon though since more often than not the newsletters I add... - Source: Hacker News / almost 4 years ago

I'm planning to build a business on this, so probably won't open-source it--but I'm always looking for interesting things to write about! I write a weekly newsletter called Future of Discovery[1]; I might write up some more implementation details there in a week or two. In the mean time, most of the heavy lifting is done by the Surprise python lib[2]. It's pretty easy to play around with, just give it a csv of... - Source: Hacker News / almost 4 years ago

FastText is a Facebook tool that, among other things, is used to train text classification models. Unlike Tensorflow.js, it is more intended to work with text so we don't need to pass a tensor and we can use the text directly. Training a model with it is much faster and there are fewer hyperparameters. Besides, to use the model from the browser is possible through WebAssembly. So it's a good alternative to try.... - Source: dev.to / almost 4 years ago