Floundering

Haven't been making much progress lately. Trying to get back on track.

I was kind of confused about where to go. Understanding the Stanford NLP parser is kind of confusing, but there may be an easy element to tackle. The output of the parse is an XML block. One of the elements should be for "time". If I could parse my data, and look for the "time" tags, I could figure out a way to work with that.

The first step is getting the parser to work. I've used the interactive shell, but haven't run the code as a batch process on my data.

---
Got the parser to run. Similar to the interactive shell, I had to remove the "annotators" flag and options, for some reason having them in there causes the output to be empty (perhaps the example code is outdated).

Tried to just run the parser on my data. After flailing for many minutes, it seemed to crash with a garbage collection error. Out of memory. I'll try to do this stuff on a smaller subset. Later.