I'd like to supplement the open call for taggers with a few points:
- Tagging is a neglected cause area. There is still a huge amount to do, and tagging makes a real difference in making LessWrong content easier to discover, explore, and re-find.
- The problem is real. People find LessWrong difficult to read because it is full of deep inferential distances and special jargon. Tags offer an easy way to disambiguate jargon, and reference all the relevant material on a subject.
- Tagging isn't just altruistic. Want to promote an idea/topic? Tagging posts and writing a good tag description is a great way to make that topic easier to discover and explore. If writing blobs of text which lots of people later read pumps your ego, tagging is a good way to do that. Write that tag before someone else! But it's also useful -- not just to other people, but also, to yourself. Tagging posts on subjects you love, and upvoting the tag on the most relevant ones, will make it easier for you to reference them later.
- You will probably discover things you want to read. Tagging naturally gets you searching for content on LessWrong related to your favorite topics. You are likely to discover than more has been written on these topics than you previously realized.
- Tagging is easy. Whenever you think of a tag you want to exist (usually because you're reading a post and decide to tag it with something, only to discover the tag doesn't exist yet), just do a search for that thing on LessWrong and tag all the relevant results! There are other approaches, of course, but if everyone did this, then we'd be in a pretty good position: any new tag created would already be put on most of the relevant posts. (This strategy doesn't work for tags which cover a significant portion of the content on LessWrong, such as the core tags, of course.)
- If you're not sure what to tag, take a look at the top posts without tags. You may want to familiarize yourself with the core tags and the concepts portal, so that you're not missing some obvious ones when you tag things.
I expect you'd get better results by using older, less hyped NLP techniques that are designed for this sort of thing:
https://stackoverflow.com/questions/15377290/unsupervised-automatic-tagging-algorithms
The tagging work that's already been done need not be a waste, because you can essentially use it as training data for the kind of tags you'd like an automated system to discover and assign. For example, tweak the hyperparameters of the topic modeling system until it is really good at independently rediscovering/reassigning the tags that have already been manually assigned.
An advantage of the automated approach is that you should be able to reapply it to some other document corpus--for example, autogenerate tags for the EA Forum, or all AI alignment related papers/discussion off LW, or the entire AI literature in order to help with/substitute for this job https://intelligence.org/2017/12/12/ml-living-library/ (especially if you can get some kind of hierarchical tagging to work)
I've actually spent a while thinking about this sort of problem and I'm happy to video call and chat more if you want.