Milabot: A Deep Reinforcement Learning Chatbot | Hacker News Reader

Milabot: A Deep Reinforcement Learning Chatbot

arxiv.org

91 pointsindescions_201716 comments

Really throwing the whole kitchen sink at the problem here. They're basically running a RL algo over an ensemble of every successful NLP algo of the last decade.

Your summary of the paper is both succint and accurate.

What's really interesting to me is that this approach yields state-of-the-art chatbot results, significantly outperforming other, non-ensemble approaches.

It makes me wonder if the subconscious part of the human mind does something similar, i.e., when faced with the task of articulating a response, does the brain subconsciously evaluate a range of possible responses, each generated by different subsystems, and then choose the best of these responses or some mixture of them, to respond?

Maybe that, or maybe you have a large number of strategies for generating replies, and you can pick a good one ahead of time, so you don't need to do an exhaustive search.

Compare it to how a human chess player looks at several possible moves as opposed to a computer program which will consider thousands.

AI is still very much a search problem -- leveraging what computers are actually good at doing to try to mimic doing things that they aren't good at.

If I ask it a question and then ask it the same question 5 minutes later will I get the same answer? If I tell it something about myself and then ask about it later, will it remember? Even the 'smartest' chat bots I have ever 'spoken' with function like someone with no functioning short-term memory or a totally ephemeral identity that alters with every statement.

Is it implemented somewhere as a real code I can run?

A machine learning paper with actual code? Hah! Not likely.

Get thee to github, there's a bunch. Not least the whole cannon of Tensorflow, but in terms of research all of the GAN stuff last year was on git as the papers hit.

Unfortunately a mostly true statement in my experience...

And papers the provide code often do not provide enough or the correct code to replicate the paper. Looking at you, XNOR-Net

Slighlty OT: Did run many chatsbots in various fields. Chatbots won't be the next big thing, not at all. Chats are a specific channel for more specific use cases, none of them created any killer app.

Maybe we need more time but chatbots got hyped for too long without any significant traction. Most are web shops/ agencies that build mediocre chatbots for brands nobody is using.

Not bashing chatbots just wondering why this topic gets upvoted again and again.

Amazon Echo and Google Home are chatbots, but with a voice interface. They seem relatively well accepted. Your thoughts?

I don't think they are - I think they are narrow assistants - order things, search for things, turn things on and off. They aren't there to have a discussion about your brothers emotional response to the Aphex Twin.

Well accepted != next big thing

> just wondering why this topic gets upvoted again and again

Because most chatbots are crap (for real world applications) because chatting is a hard problem but there's a great potential?

What's really interesting is how they designed their reward function. At the end of each chat the user can give each conversation a rating. The bot then tries to achieve a higher level of human interaction satisfaction, neat!

They say their approach relies on a minimal amount of rules, however the most prominent method in their ensemble is a rule based bot.

Reply on news.ycombinator.com