Andy Halterman

There's also a lot of info getting printed out during coding that would be nice to have logged rather than printed, while you're at it. For example, I get output...

Something like this: ``` def get_phrases(text, parse): parsed = utilities._format_parsed_str(parse) ddict = {u'test123': {u'sents': {u'0': {u'content': text, u'parsed': parsed}}, u'meta': {u'date': u'20010101'}}} return_dict = petrarch2.do_coding(ddict, None) nouns = return_dict['test123'][u'meta'][u'verbs'][u'nouns'] k...

`get_phrases` is just the thing I threw together to provide a one stop location for your verb and noun extraction needs, since I need them this week. It pulls things...

Following up on this. Are any of these (1, 2, 3, 4) complete? This is necessary for us to produce Arabic event data.

Looking at the code, that seems to handle the comparison between the extracted verb phrase and the *dictionaries*. What I'm concerned about is the ability of UniversalPetrarch to extract preps...

Just checking in on this again, especially since the preposition issue came up in Arabic. Is the code indeed extracting prepositional phrases coming off the verb? And am I right...

Great! Can you link to the part of the code that implements it, just so I can make sure I understand where it's doing it? Edit: The original implementation is...

Any update on this? This is one of the biggest obstacles to using UniversalPetrarch in production.

From talking with @JingL1014, it sounds like she has a couple theories for what could be causing the high false positives: 1. other true events in the sentences (we only...

Is there an update on this? Have you looked into those tests? It sounds from @philip-schrodt like some sentences are still producing many events so something's still going wrong.