As the author of the Android app, it's pretty interesting and exciting to see an article on this. The project was an attempt to save or at least document this language which might go extinct soon, as many others in the region did. If anyone is interested in learning more about the language or the project itself, you can contact me and I can put you in touch with the project owners.
"Many developers look at NoSQL engines—such as MongoDB, Cassandra, Redis, or Hadoop"
Noone uses Hadoop as a database. On the other hand, HBase which uses HDFS as underlying storage is a great NoSQL database that we use in production.
Nothing new here. As the article mentions, it's the Babelfish from the Hitchhiker's Guide to the Galaxy. I've wanted to build one myself since I read the book, but the fundamental problem of machines translating languages is still a very hard problem. This thing won't work.
I like the write-up, but I disagree with the reasoning to avoid STM. It sounds a lot like "avoid ConcurrentHashMap in Java". It's true that web applications mostly persist their data in a database or some other persistent structure, and obviously an STM or a ConcurrentHashMap would not do you any good for that. However; if you are working with in-memory data, then STM is a very valuable tool just like ConcurrenthHashMap is.
That was going to be my point as well. My “production” application runs light shows for electronic music events. The only state that matters is in-memory in the STM. There is no database. STM works wonderfully in the rare cases where there are multiple values which need to be changed in a coordinated way.
I like the fact that you tied the Watson api and the Telegram api together in a simple app, but it's a bit far-fetched to claim that "building intelligent bots is not too hard" based on this example.
thanks for the feedback. totally understand your point. i think the biggest problem is that the commenters here have a different understanding of the ambiguous term chatbot. the expectation is that AI or intelligent chatbot means it would pass the turing test and you would not notice if you are talking to a bot or human. but this is not the point.
everyone who has experience in natural language processing or computer vision could tell you about various sub-problems of AI which are all about equally hard. imagine you would have tried to build a similar program with the same outcome 10 years ago. you would probably be still working on it. today, you can build such a thing in one hour because multiple thousand hours of work went into the API and you can focus on the glue code. this makes it "easy" or "not too hard". AI becomes more and more available as a service and everyone can make use of it that's the whole idea
