Nathan Schneider

A related problem is that if a realization of a task fails, it is easy to miss it when other things are running in parallel. Maybe there could be an...

The `summary` mode is not documented at all in `--help`.

My guess is that the problem is in VariableHandler.scala—there seems to be a 3-layer nesting of map operations, though I'm not too familiar with Scala or this codebase. @dowobeha, any...

104–125

http://techtalks.tv/talks/the-logic-of-amr-practical-unified-graph-based-sentence-semantics-for-nlp/61564/ isn't working for me, either. I'm not aware of another way to watch the video. You could try contacting techtalks.tv to troubleshoot.

Thanks for suggesting partitioner; I hadn't seen it before. Based on the paper, it looks like it performs MWE segmentation relying on MWE-labeled training data n-gram probabilities and large lexical...

There's [one on word tokenization](http://anthology.aclweb.org/P/P12/P12-2.pdf#page=406), and [this](http://www.anthology.aclweb.org/C/C12/C12-2.pdf#page=999) and [this](https://www.scm.tees.ac.uk/users/j.read/publications/ReaDriOep13.pdf) on sentence splitting. Looking at citing papers, I see [this](http://cs.unb.ca/~ccook1/ijcnlp2013-socmed.pdf) and [this](http://link.springer.com/chapter/10.1007/978-3-319-18111-0_18#page-1) for various genres of web text. Also [this](http://anthology.aclweb.org/D/D13/D13-1146.pdf) for...

I have no particular objection to REPP, but it may be worth exploring other tools that are out there. For example, https://github.com/armatthews/TokenizeAnything is written in Python and claims to do...

Another question more broadly is what options/functionality we want the tokenizer to support. E.g., I think it would be useful to have: - an option to separate clitics like "'s"...

I don't know who made the current .bst file. Need to rerun Merlin?