GigaWord.sample.PETR.xml file without parse blocks about petrarch2 HOT 8 CLOSED

As seen in this section of the README: https://github.com/openeventdata/petrarch2/blob/master/README.md#installing under the heading StanfordNLP, PETRARCH2 no longer supports direct integration with CoreNLP, which means that raw text input is no longer supported.

from petrarch2.

from petrarch2.

The easiest way to go from text to event data is to use the full pipeline. There are step-by-step instructions here: https://andrewhalterman.com/2017/05/08/making-event-data-from-scratch-a-step-by-step-guide/

I don't think any of us have used the XML-based method in years so I'm not sure what would happen.

from petrarch2.

from petrarch2.

The XML method definitely still works -- I used it on about 25-million stories about a year ago (okay, so at least it still worked a year ago, but I don't think there have been any changes that would break it since then). However, unlike the pipeline, you need a customized program that will convert from your input format (in my case, it was the NewsML standard) to the XML standard.

from petrarch2.

from petrarch2.

If you are getting any events, then you've got things formatted correctly, and definitely keep the block, since that is where the program is getting the information. Usually, however, PETRARCH is used to code individual sentences, rather than paragraphs (in fact I'm not sure what it would do with a paragraph-length Stanford parse, though probably it would stop at the end of the first sentence), so you'll probably get a higher yield of events if you split the paragraphs into sentences.

The number of events generated will very much depend on the texts you are trying to code (the existing verbs dictionary is designed to primarily code events associated with political conflict situations, since that was the focus of the CAMEO ontology) and the actor dictionaries you are using. You can over-ride the actor dictionaries and have the program produce any events where it finds a verb phrase in the dictionary by setting the variable new_actor_length in the file PETR_config.ini to a value > 0: I'd suggest something in the range 15 - 35 -- the higher the number, the more cases you will get. It is also relatively easy to add in actors to the dictionaries if you are interested in specific cases.

from petrarch2.

from petrarch2.